Computer Vision Engineer
For developers who want to build vision systems. Learn image processing, deep learning and 3D vision, then train, optimize and deploy models on cloud and edge hardware.
{"nodes":[{"id":"title","type":"title","position":{"x":0,"y":0},"data":{"label":"Computer Vision Engineer"},"width":1688,"height":61,"style":{"width":1688,"height":61},"measured":{"width":1688,"height":61},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":0,"y":0}},{"id":"summary","type":"paragraph","position":{"x":404,"y":77},"data":{"label":"For developers who want to build vision systems. Learn image processing, deep learning and 3D vision, then train, optimize and deploy models on cloud and edge hardware."},"width":880,"height":56,"style":{"width":880,"height":56},"measured":{"width":880,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":404,"y":77}},{"id":"meta","type":"paragraph","position":{"x":524,"y":147},"data":{"label":"10 STAGES · 41 TOPICS · 151 SUBTOPICS","style":{"fontSize":13,"fontFamily":"jetbrains","fontWeight":500,"color":"var(--color-fg-subtle)"}},"width":640,"height":21,"style":{"width":640,"height":21},"measured":{"width":640,"height":21},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":524,"y":147}},{"id":"stage-1","type":"section","position":{"x":0,"y":224},"data":{"label":"Foundations","description":"Build the math, programming and tooling base needed for image processing and deep learning work.","number":1},"width":824,"height":995,"style":{"width":824,"height":995},"measured":{"width":824,"height":995},"zIndex":-999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":0,"y":224}},{"id":"topic-1-1","type":"topic","position":{"x":28,"y":345},"data":{"label":"Mathematics","number":"1.1"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":345}},{"id":"sub-1-1-1","type":"subtopic","position":{"x":28,"y":413},"data":{"label":"Linear Algebra","description":"Vectors · Matrices · Eigenvalues · SVD · Tensors"},"width":248,"height":104,"style":{"width":248,"height":104},"measured":{"width":248,"height":104},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":413}},{"id":"sub-1-1-2","type":"subtopic","position":{"x":288,"y":413},"data":{"label":"Calculus","description":"Derivatives · Gradients · Chain Rule · Jacobians"},"width":248,"height":104,"style":{"width":248,"height":104},"measured":{"width":248,"height":104},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":413}},{"id":"sub-1-1-3","type":"subtopic","position":{"x":548,"y":413},"data":{"label":"Probability and Statistics","description":"Distributions · Bayes' Theorem · MAP Estimation · Hypothesis Testing"},"width":248,"height":104,"style":{"width":248,"height":104},"measured":{"width":248,"height":104},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":413}},{"id":"sub-1-1-4","type":"subtopic","position":{"x":28,"y":529},"data":{"label":"Optimization","description":"Gradient Descent · Convex Optimization · Lagrange Multipliers"},"width":248,"height":104,"style":{"width":248,"height":104},"measured":{"width":248,"height":104},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":529}},{"id":"topic-1-2","type":"topic","position":{"x":28,"y":661},"data":{"label":"Python for Vision","number":"1.2"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":661}},{"id":"sub-1-2-1","type":"subtopic","position":{"x":28,"y":729},"data":{"label":"Core Python","description":"Data Structures · Functions · Classes · Typing"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":729}},{"id":"sub-1-2-2","type":"subtopic","position":{"x":288,"y":729},"data":{"label":"Scientific Stack","description":"NumPy · SciPy · pandas · Matplotlib"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":729}},{"id":"sub-1-2-3","type":"subtopic","position":{"x":548,"y":729},"data":{"label":"Image Libraries","description":"OpenCV · Pillow · scikit-image"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":729}},{"id":"topic-1-3","type":"topic","position":{"x":28,"y":842},"data":{"label":"C++ for Vision","number":"1.3"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":842}},{"id":"sub-1-3-1","type":"subtopic","position":{"x":28,"y":910},"data":{"label":"Modern C++","description":"Pointers · Memory Management · STL · Smart Pointers"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":910}},{"id":"sub-1-3-2","type":"subtopic","position":{"x":288,"y":910},"data":{"label":"Build Tooling","description":"CMake · vcpkg · Conan"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":910}},{"id":"sub-1-3-3","type":"subtopic","position":{"x":548,"y":910},"data":{"label":"OpenCV C++ API"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":910}},{"id":"topic-1-4","type":"topic","position":{"x":28,"y":1023},"data":{"label":"Developer Tooling","number":"1.4"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":1023}},{"id":"sub-1-4-1","type":"subtopic","position":{"x":28,"y":1091},"data":{"label":"Version Control","description":"Git · GitHub · Branching · Code Review"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":1091}},{"id":"sub-1-4-2","type":"subtopic","position":{"x":288,"y":1091},"data":{"label":"Linux and Shell","description":"Bash · CLI Utilities · SSH"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":1091}},{"id":"sub-1-4-3","type":"subtopic","position":{"x":548,"y":1091},"data":{"label":"Environments","description":"uv · Conda · Docker"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":1091}},{"id":"stage-2","type":"section","position":{"x":864,"y":224},"data":{"label":"Image Processing Fundamentals","description":"Understand how images are formed, stored and transformed using classical, non-learned techniques.","number":2},"width":824,"height":995,"style":{"width":824,"height":995},"measured":{"width":824,"height":995},"zIndex":-999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":864,"y":224}},{"id":"topic-2-1","type":"topic","position":{"x":892,"y":345},"data":{"label":"Digital Image Representation","number":"2.1"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":345}},{"id":"sub-2-1-1","type":"subtopic","position":{"x":892,"y":413},"data":{"label":"Pixels and Resolution","description":"Bit Depth · Channels · Aspect Ratio"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":413}},{"id":"sub-2-1-2","type":"subtopic","position":{"x":1152,"y":413},"data":{"label":"Color Spaces","description":"RGB · HSV · YCbCr · Lab · Grayscale"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":413}},{"id":"sub-2-1-3","type":"subtopic","position":{"x":1412,"y":413},"data":{"label":"Image Formats","description":"JPEG · PNG · TIFF · RAW · WebP"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":413}},{"id":"sub-2-1-4","type":"subtopic","position":{"x":892,"y":510},"data":{"label":"Image Sensors and ISP","description":"Demosaicing · White Balance · Noise · Exposure"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":510}},{"id":"topic-2-2","type":"topic","position":{"x":892,"y":623},"data":{"label":"Image Enhancement and Filtering","number":"2.2"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":623}},{"id":"sub-2-2-1","type":"subtopic","position":{"x":892,"y":691},"data":{"label":"Point Operations","description":"Histogram Equalization · Thresholding · Gamma Correction"},"width":248,"height":104,"style":{"width":248,"height":104},"measured":{"width":248,"height":104},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":691}},{"id":"sub-2-2-2","type":"subtopic","position":{"x":1152,"y":691},"data":{"label":"Spatial Filtering","description":"Convolution · Gaussian Blur · Median Filter · Bilateral Filter"},"width":248,"height":104,"style":{"width":248,"height":104},"measured":{"width":248,"height":104},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":691}},{"id":"sub-2-2-3","type":"subtopic","position":{"x":1412,"y":691},"data":{"label":"Frequency Domain","description":"Fourier Transform · Low-Pass Filters · High-Pass Filters · Wavelets"},"width":248,"height":104,"style":{"width":248,"height":104},"measured":{"width":248,"height":104},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":691}},{"id":"sub-2-2-4","type":"subtopic","position":{"x":892,"y":807},"data":{"label":"Morphological Operations","description":"Dilation · Erosion · Opening · Closing"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":807}},{"id":"sub-2-2-5","type":"subtopic","position":{"x":1152,"y":807},"data":{"label":"Geometric Transformations","description":"Affine · Perspective · Homography · Warping"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":807}},{"id":"topic-2-3","type":"topic","position":{"x":892,"y":920},"data":{"label":"Features and Matching","number":"2.3"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":920}},{"id":"sub-2-3-1","type":"subtopic","position":{"x":892,"y":988},"data":{"label":"Edge Detection","description":"Sobel · Canny · Laplacian"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":988}},{"id":"sub-2-3-2","type":"subtopic","position":{"x":1152,"y":988},"data":{"label":"Corner and Blob Detection","description":"Harris · Shi-Tomasi · LoG · DoG · MSER"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":988}},{"id":"sub-2-3-3","type":"subtopic","position":{"x":1412,"y":988},"data":{"label":"Local Descriptors","description":"SIFT · ORB · FAST · BRIEF"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":988}},{"id":"sub-2-3-4","type":"subtopic","position":{"x":892,"y":1085},"data":{"label":"Feature Matching","description":"Brute Force · FLANN · Ratio Test · RANSAC"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":1085}},{"id":"sub-2-3-5","type":"subtopic","position":{"x":1152,"y":1085},"data":{"label":"Image Registration and Stitching","description":"Alignment · Panoramas · Blending"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":1085}},{"id":"stage-3","type":"section","position":{"x":0,"y":1259},"data":{"label":"Machine Learning Basics","description":"Learn classical ML algorithms and evaluation practices that carry over directly to vision models.","number":3},"width":824,"height":1197,"style":{"width":824,"height":1197},"measured":{"width":824,"height":1197},"zIndex":-999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":0,"y":1259}},{"id":"topic-3-1","type":"topic","position":{"x":28,"y":1380},"data":{"label":"Supervised Learning","number":"3.1"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":1380}},{"id":"sub-3-1-1","type":"subtopic","position":{"x":28,"y":1448},"data":{"label":"Regression","description":"Linear · Ridge · Lasso · Polynomial"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":1448}},{"id":"sub-3-1-2","type":"subtopic","position":{"x":288,"y":1448},"data":{"label":"Classification","description":"Logistic Regression · SVM · k-NN · Naive Bayes"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":1448}},{"id":"sub-3-1-3","type":"subtopic","position":{"x":548,"y":1448},"data":{"label":"Tree Ensembles","description":"Decision Trees · Random Forests · XGBoost · LightGBM"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":1448}},{"id":"topic-3-2","type":"topic","position":{"x":28,"y":1561},"data":{"label":"Unsupervised Learning","number":"3.2"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":1561}},{"id":"sub-3-2-1","type":"subtopic","position":{"x":28,"y":1629},"data":{"label":"Clustering","description":"K-Means · DBSCAN · Hierarchical · Mean Shift"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":1629}},{"id":"sub-3-2-2","type":"subtopic","position":{"x":288,"y":1629},"data":{"label":"Dimensionality Reduction","description":"PCA · t-SNE · UMAP"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":1629}},{"id":"topic-3-3","type":"topic","position":{"x":28,"y":1742},"data":{"label":"Evaluation and Validation","number":"3.3"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":1742}},{"id":"sub-3-3-1","type":"subtopic","position":{"x":28,"y":1810},"data":{"label":"Classification Metrics","description":"Precision · Recall · F1 · ROC-AUC · Confusion Matrix"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":1810}},{"id":"sub-3-3-2","type":"subtopic","position":{"x":288,"y":1810},"data":{"label":"Regression Metrics","description":"MSE · RMSE · MAE · R-Squared"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":1810}},{"id":"sub-3-3-3","type":"subtopic","position":{"x":548,"y":1810},"data":{"label":"Validation Strategies","description":"Hold-Out · K-Fold · Stratification · Data Leakage"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":1810}},{"id":"stage-4","type":"section","position":{"x":864,"y":1259},"data":{"label":"Deep Learning Fundamentals","description":"Train neural networks in PyTorch and master the CNN architectures that shaped computer vision.","number":4},"width":824,"height":1197,"style":{"width":824,"height":1197},"measured":{"width":824,"height":1197},"zIndex":-999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":864,"y":1259}},{"id":"topic-4-1","type":"topic","position":{"x":892,"y":1380},"data":{"label":"Neural Network Basics","number":"4.1"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":1380}},{"id":"sub-4-1-1","type":"subtopic","position":{"x":892,"y":1448},"data":{"label":"Perceptrons and MLPs","description":"Activation Functions · Universal Approximation"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":1448}},{"id":"sub-4-1-2","type":"subtopic","position":{"x":1152,"y":1448},"data":{"label":"Backpropagation and Losses","description":"Autograd · Cross-Entropy · Focal Loss"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":1448}},{"id":"sub-4-1-3","type":"subtopic","position":{"x":1412,"y":1448},"data":{"label":"Optimizers and Schedules","description":"SGD · Adam · AdamW · Cosine Decay · Warmup"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":1448}},{"id":"sub-4-1-4","type":"subtopic","position":{"x":892,"y":1566},"data":{"label":"Regularization","description":"Dropout · Weight Decay · Normalization Layers · Label Smoothing"},"width":248,"height":104,"style":{"width":248,"height":104},"measured":{"width":248,"height":104},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":1566}},{"id":"topic-4-2","type":"topic","position":{"x":892,"y":1698},"data":{"label":"PyTorch for Vision","number":"4.2"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":1698}},{"id":"sub-4-2-1","type":"subtopic","position":{"x":892,"y":1766},"data":{"label":"Tensors and Autograd"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":1766}},{"id":"sub-4-2-2","type":"subtopic","position":{"x":1152,"y":1766},"data":{"label":"Datasets and DataLoaders","description":"torchvision · Transforms · Albumentations"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":1766}},{"id":"sub-4-2-3","type":"subtopic","position":{"x":1412,"y":1766},"data":{"label":"Training Loops","description":"Mixed Precision · Checkpointing · PyTorch Lightning"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":1766}},{"id":"sub-4-2-4","type":"subtopic","position":{"x":892,"y":1863},"data":{"label":"Experiment Tracking","description":"Weights & Biases · MLflow · TensorBoard"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":1863}},{"id":"topic-4-3","type":"topic","position":{"x":892,"y":1976},"data":{"label":"Convolutional Neural Networks","number":"4.3"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":1976}},{"id":"sub-4-3-1","type":"subtopic","position":{"x":892,"y":2044},"data":{"label":"Core Concepts","description":"Convolution · Pooling · Stride · Padding · Receptive Field"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":2044}},{"id":"sub-4-3-2","type":"subtopic","position":{"x":1152,"y":2044},"data":{"label":"Classic Architectures","description":"AlexNet · VGG · Inception · ResNet · DenseNet"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":2044}},{"id":"sub-4-3-3","type":"subtopic","position":{"x":1412,"y":2044},"data":{"label":"Modern CNNs","description":"EfficientNet · RegNet · ConvNeXt"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":2044}},{"id":"sub-4-3-4","type":"subtopic","position":{"x":892,"y":2141},"data":{"label":"Lightweight CNNs","description":"MobileNet · ShuffleNet · GhostNet"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":2141}},{"id":"topic-4-4","type":"topic","position":{"x":892,"y":2254},"data":{"label":"Data Augmentation","number":"4.4"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":2254}},{"id":"sub-4-4-1","type":"subtopic","position":{"x":892,"y":2322},"data":{"label":"Geometric and Photometric Augmentation","description":"Flips · Crops · Rotations · Color Jitter"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":2322}},{"id":"sub-4-4-2","type":"subtopic","position":{"x":1152,"y":2322},"data":{"label":"Mixing Strategies","description":"Mixup · CutMix · Mosaic"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":2322}},{"id":"sub-4-4-3","type":"subtopic","position":{"x":1412,"y":2322},"data":{"label":"Automated Augmentation","description":"AutoAugment · RandAugment · TrivialAugment"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":2322}},{"id":"stage-5","type":"section","position":{"x":0,"y":2495},"data":{"label":"Modern Vision Architectures","description":"Move beyond CNNs to vision transformers, self-supervised learning and vision-language foundation models.","number":5},"width":824,"height":1060,"style":{"width":824,"height":1060},"measured":{"width":824,"height":1060},"zIndex":-999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":0,"y":2495}},{"id":"topic-5-1","type":"topic","position":{"x":28,"y":2616},"data":{"label":"Attention and Vision Transformers","number":"5.1"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":2616}},{"id":"sub-5-1-1","type":"subtopic","position":{"x":28,"y":2684},"data":{"label":"Attention Mechanisms","description":"Self-Attention · Cross-Attention · Multi-Head Attention"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":2684}},{"id":"sub-5-1-2","type":"subtopic","position":{"x":288,"y":2684},"data":{"label":"Vision Transformers","description":"ViT · DeiT · Swin Transformer"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":2684}},{"id":"sub-5-1-3","type":"subtopic","position":{"x":548,"y":2684},"data":{"label":"Efficient Attention","description":"Windowed Attention · FlashAttention · Token Merging"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":2684}},{"id":"topic-5-2","type":"topic","position":{"x":28,"y":2797},"data":{"label":"Transfer Learning and Fine-Tuning","number":"5.2"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":2797}},{"id":"sub-5-2-1","type":"subtopic","position":{"x":28,"y":2865},"data":{"label":"Pretrained Backbones","description":"timm · torchvision · Hugging Face Hub"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":2865}},{"id":"sub-5-2-2","type":"subtopic","position":{"x":288,"y":2865},"data":{"label":"Fine-Tuning Strategies","description":"Linear Probing · Full Fine-Tuning · Layer Freezing"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":2865}},{"id":"sub-5-2-3","type":"subtopic","position":{"x":548,"y":2865},"data":{"label":"Parameter-Efficient Fine-Tuning","description":"LoRA · QLoRA · Adapters"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":2865}},{"id":"topic-5-3","type":"topic","position":{"x":28,"y":2980},"data":{"label":"Self-Supervised Learning","number":"5.3"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":2980}},{"id":"sub-5-3-1","type":"subtopic","position":{"x":28,"y":3048},"data":{"label":"Contrastive Methods","description":"SimCLR · MoCo · BYOL"},"width":248,"height":67,"style":{"width":248,"height":67},"measured":{"width":248,"height":67},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":3048}},{"id":"sub-5-3-2","type":"subtopic","position":{"x":288,"y":3048},"data":{"label":"Masked Image Modeling","description":"MAE · BEiT"},"width":248,"height":67,"style":{"width":248,"height":67},"measured":{"width":248,"height":67},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":3048}},{"id":"sub-5-3-3","type":"subtopic","position":{"x":548,"y":3048},"data":{"label":"Self-Distillation","description":"DINOv2 · DINOv3"},"width":248,"height":67,"style":{"width":248,"height":67},"measured":{"width":248,"height":67},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":3048}},{"id":"topic-5-4","type":"topic","position":{"x":28,"y":3143},"data":{"label":"Vision-Language Models","number":"5.4"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":3143}},{"id":"sub-5-4-1","type":"subtopic","position":{"x":28,"y":3211},"data":{"label":"Contrastive Image-Text Models","description":"CLIP · SigLIP · OpenCLIP"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":3211}},{"id":"sub-5-4-2","type":"subtopic","position":{"x":288,"y":3211},"data":{"label":"Multimodal LLMs","description":"LLaVA · Qwen-VL · InternVL · Gemini"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":3211}},{"id":"sub-5-4-3","type":"subtopic","position":{"x":548,"y":3211},"data":{"label":"Open-Vocabulary Detection","description":"Grounding DINO · OWL-ViT · YOLO-World"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":3211}},{"id":"sub-5-4-4","type":"subtopic","position":{"x":28,"y":3310},"data":{"label":"Few-Shot and Zero-Shot Learning","description":"Prototypical Networks · MAML · Visual Prompting"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":3310}},{"id":"stage-6","type":"section","position":{"x":864,"y":2495},"data":{"label":"Core Vision Tasks","description":"Solve the main perception tasks: detection, segmentation, pose estimation and document understanding.","number":6},"width":824,"height":1060,"style":{"width":824,"height":1060},"measured":{"width":824,"height":1060},"zIndex":-999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":864,"y":2495}},{"id":"topic-6-1","type":"topic","position":{"x":892,"y":2616},"data":{"label":"Object Detection","number":"6.1"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":2616}},{"id":"sub-6-1-1","type":"subtopic","position":{"x":892,"y":2684},"data":{"label":"Two-Stage Detectors","description":"R-CNN · Fast R-CNN · Faster R-CNN · Cascade R-CNN"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":2684}},{"id":"sub-6-1-2","type":"subtopic","position":{"x":1152,"y":2684},"data":{"label":"One-Stage Detectors","description":"YOLO Family · SSD · RetinaNet"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":2684}},{"id":"sub-6-1-3","type":"subtopic","position":{"x":1412,"y":2684},"data":{"label":"Anchor-Free Detectors","description":"FCOS · CenterNet · CornerNet"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":2684}},{"id":"sub-6-1-4","type":"subtopic","position":{"x":892,"y":2781},"data":{"label":"Transformer Detectors","description":"DETR · Deformable DETR · RT-DETR · RF-DETR"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":2781}},{"id":"sub-6-1-5","type":"subtopic","position":{"x":1152,"y":2781},"data":{"label":"Detection Evaluation","description":"IoU · mAP · Precision-Recall Curves · NMS"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":2781}},{"id":"topic-6-2","type":"topic","position":{"x":892,"y":2894},"data":{"label":"Image Segmentation","number":"6.2"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":2894}},{"id":"sub-6-2-1","type":"subtopic","position":{"x":892,"y":2962},"data":{"label":"Semantic Segmentation","description":"FCN · U-Net · DeepLabV3+ · SegFormer"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":2962}},{"id":"sub-6-2-2","type":"subtopic","position":{"x":1152,"y":2962},"data":{"label":"Instance Segmentation","description":"Mask R-CNN · YOLACT · PointRend"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":2962}},{"id":"sub-6-2-3","type":"subtopic","position":{"x":1412,"y":2962},"data":{"label":"Panoptic and Universal Segmentation","description":"Panoptic FPN · Mask2Former · OneFormer"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":2962}},{"id":"sub-6-2-4","type":"subtopic","position":{"x":892,"y":3080},"data":{"label":"Promptable Segmentation","description":"SAM · SAM 2 · SAM 3"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":3080}},{"id":"sub-6-2-5","type":"subtopic","position":{"x":1152,"y":3080},"data":{"label":"Segmentation Metrics","description":"Pixel Accuracy · Mean IoU · Dice Coefficient"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":3080}},{"id":"topic-6-3","type":"topic","position":{"x":892,"y":3193},"data":{"label":"Pose Estimation and Keypoints","number":"6.3"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":3193}},{"id":"sub-6-3-1","type":"subtopic","position":{"x":892,"y":3261},"data":{"label":"2D Human Pose","description":"HRNet · ViTPose · RTMPose · MediaPipe"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":3261}},{"id":"sub-6-3-2","type":"subtopic","position":{"x":1152,"y":3261},"data":{"label":"Hand and Face Landmarks","description":"Hand Tracking · Face Mesh · Landmark Regression"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":3261}},{"id":"sub-6-3-3","type":"subtopic","position":{"x":1412,"y":3261},"data":{"label":"3D Pose and Body Models","description":"2D-to-3D Lifting · SMPL · Multi-View Capture"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":3261}},{"id":"topic-6-4","type":"topic","position":{"x":892,"y":3374},"data":{"label":"Document and Text Analysis","number":"6.4"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":3374}},{"id":"sub-6-4-1","type":"subtopic","position":{"x":892,"y":3442},"data":{"label":"Text Detection and OCR","description":"Tesseract · PaddleOCR · EasyOCR · CRNN"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":3442}},{"id":"sub-6-4-2","type":"subtopic","position":{"x":1152,"y":3442},"data":{"label":"Document Understanding","description":"LayoutLMv3 · Donut · TrOCR"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":3442}},{"id":"sub-6-4-3","type":"subtopic","position":{"x":1412,"y":3442},"data":{"label":"VLM Document Parsing","description":"Tables · Forms · Structured Output"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":3442}},{"id":"stage-7","type":"section","position":{"x":0,"y":3595},"data":{"label":"Video and Generative Vision","description":"Analyze motion and time in video, and generate or edit images and video with modern generative models.","number":7},"width":824,"height":1224,"style":{"width":824,"height":1224},"measured":{"width":824,"height":1224},"zIndex":-999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":0,"y":3595}},{"id":"topic-7-1","type":"topic","position":{"x":28,"y":3716},"data":{"label":"Motion Analysis","number":"7.1"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":3716}},{"id":"sub-7-1-1","type":"subtopic","position":{"x":28,"y":3784},"data":{"label":"Optical Flow","description":"Lucas-Kanade · Horn-Schunck · RAFT"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":3784}},{"id":"sub-7-1-2","type":"subtopic","position":{"x":288,"y":3784},"data":{"label":"Background Subtraction","description":"Frame Differencing · MOG2 · KNN"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":3784}},{"id":"topic-7-2","type":"topic","position":{"x":28,"y":3897},"data":{"label":"Object Tracking","number":"7.2"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":3897}},{"id":"sub-7-2-1","type":"subtopic","position":{"x":28,"y":3965},"data":{"label":"Single Object Tracking","description":"Siamese Networks · SiamRPN · OSTrack"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":3965}},{"id":"sub-7-2-2","type":"subtopic","position":{"x":288,"y":3965},"data":{"label":"Multi-Object Tracking","description":"SORT · DeepSORT · ByteTrack · BoT-SORT · OC-SORT"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":3965}},{"id":"sub-7-2-3","type":"subtopic","position":{"x":548,"y":3965},"data":{"label":"Tracking Metrics","description":"MOTA · IDF1 · HOTA"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":3965}},{"id":"topic-7-3","type":"topic","position":{"x":28,"y":4078},"data":{"label":"Video Understanding","number":"7.3"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":4078}},{"id":"sub-7-3-1","type":"subtopic","position":{"x":28,"y":4146},"data":{"label":"Two-Stream Networks","description":"Spatial Stream · Temporal Stream"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":4146}},{"id":"sub-7-3-2","type":"subtopic","position":{"x":288,"y":4146},"data":{"label":"3D CNNs","description":"C3D · I3D · SlowFast · X3D"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":4146}},{"id":"sub-7-3-3","type":"subtopic","position":{"x":548,"y":4146},"data":{"label":"Video Transformers","description":"TimeSformer · ViViT · VideoMAE"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":4146}},{"id":"sub-7-3-4","type":"subtopic","position":{"x":28,"y":4243},"data":{"label":"Skeleton-Based Action Recognition","description":"ST-GCN · Graph Convolutions"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":4243}},{"id":"topic-7-4","type":"topic","position":{"x":28,"y":4358},"data":{"label":"Image Generation","number":"7.4"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":4358}},{"id":"sub-7-4-1","type":"subtopic","position":{"x":28,"y":4426},"data":{"label":"GANs","description":"DCGAN · StyleGAN · Pix2Pix · CycleGAN"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":4426}},{"id":"sub-7-4-2","type":"subtopic","position":{"x":288,"y":4426},"data":{"label":"Autoencoders and Tokenizers","description":"VAE · VQ-VAE · VQGAN"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":4426}},{"id":"sub-7-4-3","type":"subtopic","position":{"x":548,"y":4426},"data":{"label":"Diffusion Models","description":"DDPM · DDIM · Latent Diffusion · Diffusion Transformers"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":4426}},{"id":"sub-7-4-4","type":"subtopic","position":{"x":28,"y":4525},"data":{"label":"Controllable Generation","description":"ControlNet · IP-Adapter · Inpainting · LoRA"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":4525}},{"id":"sub-7-4-5","type":"subtopic","position":{"x":288,"y":4525},"data":{"label":"Generative Metrics","description":"FID · Inception Score · CLIP Score"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":4525}},{"id":"topic-7-5","type":"topic","position":{"x":28,"y":4638},"data":{"label":"Video Generation and Enhancement","number":"7.5"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":4638}},{"id":"sub-7-5-1","type":"subtopic","position":{"x":28,"y":4706},"data":{"label":"Text-to-Video Models","description":"Sora · Veo · Wan · HunyuanVideo"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":4706}},{"id":"sub-7-5-2","type":"subtopic","position":{"x":288,"y":4706},"data":{"label":"Video Super-Resolution","description":"BasicVSR · Real-ESRGAN · Temporal Consistency"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":4706}},{"id":"sub-7-5-3","type":"subtopic","position":{"x":548,"y":4706},"data":{"label":"Frame Interpolation","description":"RIFE · FILM · Motion Estimation"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":4706}},{"id":"stage-8","type":"section","position":{"x":864,"y":3595},"data":{"label":"3D Computer Vision","description":"Recover geometry from images and work with depth, point clouds and neural 3D scene representations.","number":8},"width":824,"height":1224,"style":{"width":824,"height":1224},"measured":{"width":824,"height":1224},"zIndex":-999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":864,"y":3595}},{"id":"topic-8-1","type":"topic","position":{"x":892,"y":3716},"data":{"label":"Camera Geometry and Calibration","number":"8.1"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":3716}},{"id":"sub-8-1-1","type":"subtopic","position":{"x":892,"y":3784},"data":{"label":"Pinhole Camera Model","description":"Intrinsics · Extrinsics · Projection"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":3784}},{"id":"sub-8-1-2","type":"subtopic","position":{"x":1152,"y":3784},"data":{"label":"Camera Calibration","description":"Checkerboard Targets · Lens Distortion · Reprojection Error"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":3784}},{"id":"sub-8-1-3","type":"subtopic","position":{"x":1412,"y":3784},"data":{"label":"Epipolar Geometry","description":"Fundamental Matrix · Essential Matrix · Triangulation"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":3784}},{"id":"topic-8-2","type":"topic","position":{"x":892,"y":3897},"data":{"label":"Depth Estimation","number":"8.2"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":3897}},{"id":"sub-8-2-1","type":"subtopic","position":{"x":892,"y":3965},"data":{"label":"Stereo Matching","description":"Disparity Maps · Block Matching · Semi-Global Matching"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":3965}},{"id":"sub-8-2-2","type":"subtopic","position":{"x":1152,"y":3965},"data":{"label":"Monocular Depth","description":"MiDaS · Depth Anything V2 · Metric Depth"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":3965}},{"id":"sub-8-2-3","type":"subtopic","position":{"x":1412,"y":3965},"data":{"label":"Depth Sensors","description":"Structured Light · Time of Flight · LiDAR"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":3965}},{"id":"topic-8-3","type":"topic","position":{"x":892,"y":4078},"data":{"label":"Point Clouds and 3D Data","number":"8.3"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":4078}},{"id":"sub-8-3-1","type":"subtopic","position":{"x":892,"y":4146},"data":{"label":"3D Representations","description":"Point Clouds · Voxels · Meshes · SDFs"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":4146}},{"id":"sub-8-3-2","type":"subtopic","position":{"x":1152,"y":4146},"data":{"label":"Point Cloud Processing","description":"Open3D · PCL · ICP Registration"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":4146}},{"id":"sub-8-3-3","type":"subtopic","position":{"x":1412,"y":4146},"data":{"label":"Point Cloud Deep Learning","description":"PointNet · PointNet++ · KPConv · Point Transformer"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":4146}},{"id":"sub-8-3-4","type":"subtopic","position":{"x":892,"y":4243},"data":{"label":"3D Object Detection","description":"VoxelNet · PointPillars · SECOND · CenterPoint"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":4243}},{"id":"topic-8-4","type":"topic","position":{"x":892,"y":4356},"data":{"label":"Structure from Motion and SLAM","number":"8.4"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":4356}},{"id":"sub-8-4-1","type":"subtopic","position":{"x":892,"y":4424},"data":{"label":"Structure from Motion","description":"COLMAP · GLOMAP · Bundle Adjustment"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":4424}},{"id":"sub-8-4-2","type":"subtopic","position":{"x":1152,"y":4424},"data":{"label":"Visual SLAM","description":"ORB-SLAM3 · DSO · Loop Closure"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":4424}},{"id":"sub-8-4-3","type":"subtopic","position":{"x":1412,"y":4424},"data":{"label":"Visual-Inertial Odometry","description":"VINS-Mono · IMU Preintegration · Sensor Fusion"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":4424}},{"id":"sub-8-4-4","type":"subtopic","position":{"x":892,"y":4521},"data":{"label":"Learned 3D Reconstruction","description":"DUSt3R · MASt3R · VGGT"},"width":248,"height":67,"style":{"width":248,"height":67},"measured":{"width":248,"height":67},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":4521}},{"id":"topic-8-5","type":"topic","position":{"x":892,"y":4616},"data":{"label":"Neural 3D Representations","number":"8.5"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":4616}},{"id":"sub-8-5-1","type":"subtopic","position":{"x":892,"y":4684},"data":{"label":"Neural Radiance Fields","description":"NeRF · Mip-NeRF · Instant NGP"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":4684}},{"id":"sub-8-5-2","type":"subtopic","position":{"x":1152,"y":4684},"data":{"label":"3D Gaussian Splatting","description":"Rasterization · Dynamic Scenes · Mesh Extraction"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":4684}},{"id":"sub-8-5-3","type":"subtopic","position":{"x":1412,"y":4684},"data":{"label":"Image-to-3D Generation","description":"Multi-View Diffusion · Text-to-3D"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":4684}},{"id":"stage-9","type":"section","position":{"x":0,"y":4858},"data":{"label":"Production, Edge AI and MLOps","description":"Prepare data, optimize models, then deploy, monitor and govern vision systems on cloud and edge hardware.","number":9},"width":824,"height":1717,"style":{"width":824,"height":1717},"measured":{"width":824,"height":1717},"zIndex":-999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":0,"y":4858}},{"id":"topic-9-1","type":"topic","position":{"x":28,"y":5001},"data":{"label":"Data Management","number":"9.1"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":5001}},{"id":"sub-9-1-1","type":"subtopic","position":{"x":28,"y":5069},"data":{"label":"Annotation Tools","description":"CVAT · Label Studio · Roboflow"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":5069}},{"id":"sub-9-1-2","type":"subtopic","position":{"x":288,"y":5069},"data":{"label":"Dataset Versioning and Curation","description":"DVC · lakeFS · FiftyOne"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":5069}},{"id":"sub-9-1-3","type":"subtopic","position":{"x":548,"y":5069},"data":{"label":"Active Learning","description":"Uncertainty Sampling · Human-in-the-Loop"},"width":248,"height":87,"style":{"width":248,"height":87},"measured":{"width":248,"height":87},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":5069}},{"id":"sub-9-1-4","type":"subtopic","position":{"x":28,"y":5168},"data":{"label":"Synthetic Data","description":"Omniverse · Unity · Blender · CARLA"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":5168}},{"id":"topic-9-2","type":"topic","position":{"x":28,"y":5281},"data":{"label":"Model Optimization","number":"9.2"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":5281}},{"id":"sub-9-2-1","type":"subtopic","position":{"x":28,"y":5349},"data":{"label":"Quantization","description":"PTQ · QAT · INT8 · FP16 · FP8"},"width":248,"height":104,"style":{"width":248,"height":104},"measured":{"width":248,"height":104},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":5349}},{"id":"sub-9-2-2","type":"subtopic","position":{"x":288,"y":5349},"data":{"label":"Pruning and Sparsity","description":"Structured Pruning · Unstructured Pruning · 2:4 Sparsity"},"width":248,"height":104,"style":{"width":248,"height":104},"measured":{"width":248,"height":104},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":5349}},{"id":"sub-9-2-3","type":"subtopic","position":{"x":548,"y":5349},"data":{"label":"Knowledge Distillation","description":"Teacher-Student · Feature Distillation"},"width":248,"height":104,"style":{"width":248,"height":104},"measured":{"width":248,"height":104},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":5349}},{"id":"sub-9-2-4","type":"subtopic","position":{"x":28,"y":5465},"data":{"label":"Hardware-Aware NAS","description":"Latency Constraints · Once-for-All"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":5465}},{"id":"sub-9-2-5","type":"subtopic","position":{"x":288,"y":5465},"data":{"label":"GPU Programming","description":"CUDA · cuDNN · Triton Kernels"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":5465}},{"id":"topic-9-3","type":"topic","position":{"x":28,"y":5578},"data":{"label":"Inference Runtimes and Compilers","number":"9.3"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":5578}},{"id":"sub-9-3-1","type":"subtopic","position":{"x":28,"y":5646},"data":{"label":"ONNX and ONNX Runtime"},"width":248,"height":67,"style":{"width":248,"height":67},"measured":{"width":248,"height":67},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":5646}},{"id":"sub-9-3-2","type":"subtopic","position":{"x":288,"y":5646},"data":{"label":"NVIDIA TensorRT","description":"FP16 · INT8 · Layer Fusion"},"width":248,"height":67,"style":{"width":248,"height":67},"measured":{"width":248,"height":67},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":5646}},{"id":"sub-9-3-3","type":"subtopic","position":{"x":548,"y":5646},"data":{"label":"Intel OpenVINO","description":"CPU · Integrated GPU · NPU"},"width":248,"height":67,"style":{"width":248,"height":67},"measured":{"width":248,"height":67},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":5646}},{"id":"sub-9-3-4","type":"subtopic","position":{"x":28,"y":5725},"data":{"label":"Deep Learning Compilers","description":"torch.compile · Apache TVM · MLIR"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":5725}},{"id":"topic-9-4","type":"topic","position":{"x":28,"y":5838},"data":{"label":"Edge and Mobile Deployment","number":"9.4"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":5838}},{"id":"sub-9-4-1","type":"subtopic","position":{"x":28,"y":5906},"data":{"label":"Edge Hardware","description":"Jetson Orin · Raspberry Pi 5 · Hailo · OAK-D"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":5906}},{"id":"sub-9-4-2","type":"subtopic","position":{"x":288,"y":5906},"data":{"label":"Mobile Runtimes","description":"LiteRT · Core ML · ExecuTorch · NCNN"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":5906}},{"id":"sub-9-4-3","type":"subtopic","position":{"x":548,"y":5906},"data":{"label":"Web Deployment","description":"ONNX Runtime Web · WebGPU · TensorFlow.js · WebAssembly"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":5906}},{"id":"sub-9-4-4","type":"subtopic","position":{"x":28,"y":6003},"data":{"label":"Edge Fleet Management","description":"OTA Updates · Remote Monitoring"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":6003}},{"id":"topic-9-5","type":"topic","position":{"x":28,"y":6116},"data":{"label":"Serving and Monitoring","number":"9.5"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":6116}},{"id":"sub-9-5-1","type":"subtopic","position":{"x":28,"y":6184},"data":{"label":"Containerization","description":"Docker · NVIDIA Container Toolkit"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":6184}},{"id":"sub-9-5-2","type":"subtopic","position":{"x":288,"y":6184},"data":{"label":"Model Serving","description":"Triton Inference Server · BentoML · KServe · Ray Serve"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":6184}},{"id":"sub-9-5-3","type":"subtopic","position":{"x":548,"y":6184},"data":{"label":"Orchestration and Pipelines","description":"Kubernetes · Kubeflow · Airflow"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":6184}},{"id":"sub-9-5-4","type":"subtopic","position":{"x":28,"y":6281},"data":{"label":"Model Registry","description":"MLflow · SageMaker · Vertex AI"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":6281}},{"id":"sub-9-5-5","type":"subtopic","position":{"x":288,"y":6281},"data":{"label":"Production Monitoring","description":"Data Drift · OOD Detection · Performance Metrics"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":6281}},{"id":"sub-9-5-6","type":"subtopic","position":{"x":548,"y":6281},"data":{"label":"Cloud Vision APIs","description":"AWS Rekognition · Google Cloud Vision · Azure AI Vision"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":6281}},{"id":"topic-9-6","type":"topic","position":{"x":28,"y":6394},"data":{"label":"Responsible Vision AI","number":"9.6"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":6394}},{"id":"sub-9-6-1","type":"subtopic","position":{"x":28,"y":6462},"data":{"label":"Bias and Fairness","description":"Dataset Bias · Demographic Parity · Debiasing"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":28,"y":6462}},{"id":"sub-9-6-2","type":"subtopic","position":{"x":288,"y":6462},"data":{"label":"Privacy Preservation","description":"Face Anonymization · Federated Learning · Differential Privacy"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":288,"y":6462}},{"id":"sub-9-6-3","type":"subtopic","position":{"x":548,"y":6462},"data":{"label":"Adversarial Robustness","description":"Adversarial Attacks · Defenses · Deepfake Detection"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":548,"y":6462}},{"id":"stage-10","type":"section","position":{"x":864,"y":4858},"data":{"label":"Applications, Capstone and Career","description":"Apply vision skills to real domains, build a portfolio of end-to-end projects and prepare for interviews.","number":10},"width":824,"height":1717,"style":{"width":824,"height":1717},"measured":{"width":824,"height":1717},"zIndex":-999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":864,"y":4858}},{"id":"topic-10-1","type":"topic","position":{"x":892,"y":4979},"data":{"label":"Domain Applications","number":"10.1"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":4979}},{"id":"sub-10-1-1","type":"subtopic","position":{"x":892,"y":5047},"data":{"label":"Autonomous Driving and Robotics","description":"Sensor Fusion · BEV Perception · Lane Detection · Occupancy"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":5047}},{"id":"sub-10-1-2","type":"subtopic","position":{"x":1152,"y":5047},"data":{"label":"Medical Imaging","description":"DICOM · NIfTI · 3D U-Net · nnU-Net · MONAI"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":5047}},{"id":"sub-10-1-3","type":"subtopic","position":{"x":1412,"y":5047},"data":{"label":"Remote Sensing","description":"Multispectral · Hyperspectral · SAR · Geospatial Foundation Models"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":5047}},{"id":"sub-10-1-4","type":"subtopic","position":{"x":892,"y":5165},"data":{"label":"Industrial Inspection","description":"Defect Detection · Anomaly Detection · Metrology"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":5165}},{"id":"topic-10-2","type":"topic","position":{"x":892,"y":5278},"data":{"label":"Capstone Projects","number":"10.2"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":5278}},{"id":"sub-10-2-1","type":"subtopic","position":{"x":892,"y":5346},"data":{"label":"Real-Time Detection App","description":"Custom Dataset · YOLO · Edge Deployment"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":5346}},{"id":"sub-10-2-2","type":"subtopic","position":{"x":1152,"y":5346},"data":{"label":"Segmentation Pipeline","description":"Annotation · Training · Evaluation · Serving"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":5346}},{"id":"sub-10-2-3","type":"subtopic","position":{"x":1412,"y":5346},"data":{"label":"3D Reconstruction Project","description":"SfM · Gaussian Splatting · Visualization"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":5346}},{"id":"sub-10-2-4","type":"subtopic","position":{"x":892,"y":5443},"data":{"label":"Vision-Language Application","description":"VLM · Visual Search · Captioning"},"width":248,"height":106,"style":{"width":248,"height":106},"measured":{"width":248,"height":106},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":5443}},{"id":"topic-10-3","type":"topic","position":{"x":892,"y":5577},"data":{"label":"Portfolio and Interviews","number":"10.3"},"width":768,"height":56,"style":{"width":768,"height":56},"measured":{"width":768,"height":56},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":5577}},{"id":"sub-10-3-1","type":"subtopic","position":{"x":892,"y":5645},"data":{"label":"Portfolio","description":"GitHub Repos · Live Demos · Technical Blog Posts"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":5645}},{"id":"sub-10-3-2","type":"subtopic","position":{"x":1152,"y":5645},"data":{"label":"Technical Interviews","description":"CV Fundamentals · Coding · ML System Design"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1152,"y":5645}},{"id":"sub-10-3-3","type":"subtopic","position":{"x":1412,"y":5645},"data":{"label":"Paper Discussions","description":"Architecture Trade-offs · Recent Research"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":1412,"y":5645}},{"id":"sub-10-3-4","type":"subtopic","position":{"x":892,"y":5742},"data":{"label":"Career Paths","description":"Perception Engineer · ML Engineer · Research Engineer"},"width":248,"height":85,"style":{"width":248,"height":85},"measured":{"width":248,"height":85},"zIndex":999,"selected":false,"selectable":true,"focusable":true,"dragging":false,"resizing":false,"positionAbsolute":{"x":892,"y":5742}}],"edges":[]}
01 Foundations Build the math, programming and tooling base needed for image processing and deep learning work. 02 Image Processing Fundamentals Understand how images are formed, stored and transformed using classical, non-learned techniques. 03 Machine Learning Basics Learn classical ML algorithms and evaluation practices that carry over directly to vision models. 04 Deep Learning Fundamentals Train neural networks in PyTorch and master the CNN architectures that shaped computer vision. 05 Modern Vision Architectures Move beyond CNNs to vision transformers, self-supervised learning and vision-language foundation models. 06 Core Vision Tasks Solve the main perception tasks: detection, segmentation, pose estimation and document understanding. 07 Video and Generative Vision Analyze motion and time in video, and generate or edit images and video with modern generative models. 08 3D Computer Vision Recover geometry from images and work with depth, point clouds and neural 3D scene representations. 09 Production, Edge AI and MLOps Prepare data, optimize models, then deploy, monitor and govern vision systems on cloud and edge hardware. 10 Applications, Capstone and Career Apply vision skills to real domains, build a portfolio of end-to-end projects and prepare for interviews. Computer Vision Engineer For developers who want to build vision systems. Learn image processing, deep learning and 3D vision, then train, optimize and deploy models on cloud and edge hardware. 10 STAGES · 41 TOPICS · 151 SUBTOPICS 1.1 Mathematics Linear Algebra Vectors · Matrices · Eigenvalues · SVD · Tensors Calculus Derivatives · Gradients · Chain Rule · Jacobians Probability and Statistics Distributions · Bayes' Theorem · MAP Estimation · Hypothesis Testing Optimization Gradient Descent · Convex Optimization · Lagrange Multipliers 1.2 Python for Vision Core Python Data Structures · Functions · Classes · Typing Scientific Stack NumPy · SciPy · pandas · Matplotlib Image Libraries OpenCV · Pillow · scikit-image 1.3 C++ for Vision Modern C++ Pointers · Memory Management · STL · Smart Pointers Build Tooling CMake · vcpkg · Conan OpenCV C++ API 1.4 Developer Tooling Version Control Git · GitHub · Branching · Code Review Linux and Shell Bash · CLI Utilities · SSH Environments uv · Conda · Docker 2.1 Digital Image Representation Pixels and Resolution Bit Depth · Channels · Aspect Ratio Color Spaces RGB · HSV · YCbCr · Lab · Grayscale Image Formats JPEG · PNG · TIFF · RAW · WebP Image Sensors and ISP Demosaicing · White Balance · Noise · Exposure 2.2 Image Enhancement and Filtering Point Operations Histogram Equalization · Thresholding · Gamma Correction Spatial Filtering Convolution · Gaussian Blur · Median Filter · Bilateral Filter Frequency Domain Fourier Transform · Low-Pass Filters · High-Pass Filters · Wavelets Morphological Operations Dilation · Erosion · Opening · Closing Geometric Transformations Affine · Perspective · Homography · Warping 2.3 Features and Matching Edge Detection Sobel · Canny · Laplacian Corner and Blob Detection Harris · Shi-Tomasi · LoG · DoG · MSER Local Descriptors SIFT · ORB · FAST · BRIEF Feature Matching Brute Force · FLANN · Ratio Test · RANSAC Image Registration and Stitching Alignment · Panoramas · Blending 3.1 Supervised Learning Regression Linear · Ridge · Lasso · Polynomial Classification Logistic Regression · SVM · k-NN · Naive Bayes Tree Ensembles Decision Trees · Random Forests · XGBoost · LightGBM 3.2 Unsupervised Learning Clustering K-Means · DBSCAN · Hierarchical · Mean Shift Dimensionality Reduction PCA · t-SNE · UMAP 3.3 Evaluation and Validation Classification Metrics Precision · Recall · F1 · ROC-AUC · Confusion Matrix Regression Metrics MSE · RMSE · MAE · R-Squared Validation Strategies Hold-Out · K-Fold · Stratification · Data Leakage 4.1 Neural Network Basics Perceptrons and MLPs Activation Functions · Universal Approximation Backpropagation and Losses Autograd · Cross-Entropy · Focal Loss Optimizers and Schedules SGD · Adam · AdamW · Cosine Decay · Warmup Regularization Dropout · Weight Decay · Normalization Layers · Label Smoothing 4.2 PyTorch for Vision Tensors and Autograd Datasets and DataLoaders torchvision · Transforms · Albumentations Training Loops Mixed Precision · Checkpointing · PyTorch Lightning Experiment Tracking Weights & Biases · MLflow · TensorBoard 4.3 Convolutional Neural Networks Core Concepts Convolution · Pooling · Stride · Padding · Receptive Field Classic Architectures AlexNet · VGG · Inception · ResNet · DenseNet Modern CNNs EfficientNet · RegNet · ConvNeXt Lightweight CNNs MobileNet · ShuffleNet · GhostNet 4.4 Data Augmentation Geometric and Photometric Augmentation Flips · Crops · Rotations · Color Jitter Mixing Strategies Mixup · CutMix · Mosaic Automated Augmentation AutoAugment · RandAugment · TrivialAugment 5.1 Attention and Vision Transformers Attention Mechanisms Self-Attention · Cross-Attention · Multi-Head Attention Vision Transformers ViT · DeiT · Swin Transformer Efficient Attention Windowed Attention · FlashAttention · Token Merging 5.2 Transfer Learning and Fine-Tuning Pretrained Backbones timm · torchvision · Hugging Face Hub Fine-Tuning Strategies Linear Probing · Full Fine-Tuning · Layer Freezing Parameter-Efficient Fine-Tuning LoRA · QLoRA · Adapters 5.3 Self-Supervised Learning Contrastive Methods SimCLR · MoCo · BYOL Masked Image Modeling MAE · BEiT Self-Distillation DINOv2 · DINOv3 5.4 Vision-Language Models Contrastive Image-Text Models CLIP · SigLIP · OpenCLIP Multimodal LLMs LLaVA · Qwen-VL · InternVL · Gemini Open-Vocabulary Detection Grounding DINO · OWL-ViT · YOLO-World Few-Shot and Zero-Shot Learning Prototypical Networks · MAML · Visual Prompting 6.1 Object Detection Two-Stage Detectors R-CNN · Fast R-CNN · Faster R-CNN · Cascade R-CNN One-Stage Detectors YOLO Family · SSD · RetinaNet Anchor-Free Detectors FCOS · CenterNet · CornerNet Transformer Detectors DETR · Deformable DETR · RT-DETR · RF-DETR Detection Evaluation IoU · mAP · Precision-Recall Curves · NMS 6.2 Image Segmentation Semantic Segmentation FCN · U-Net · DeepLabV3+ · SegFormer Instance Segmentation Mask R-CNN · YOLACT · PointRend Panoptic and Universal Segmentation Panoptic FPN · Mask2Former · OneFormer Promptable Segmentation SAM · SAM 2 · SAM 3 Segmentation Metrics Pixel Accuracy · Mean IoU · Dice Coefficient 6.3 Pose Estimation and Keypoints 2D Human Pose HRNet · ViTPose · RTMPose · MediaPipe Hand and Face Landmarks Hand Tracking · Face Mesh · Landmark Regression 3D Pose and Body Models 2D-to-3D Lifting · SMPL · Multi-View Capture 6.4 Document and Text Analysis Text Detection and OCR Tesseract · PaddleOCR · EasyOCR · CRNN Document Understanding LayoutLMv3 · Donut · TrOCR VLM Document Parsing Tables · Forms · Structured Output 7.1 Motion Analysis Optical Flow Lucas-Kanade · Horn-Schunck · RAFT Background Subtraction Frame Differencing · MOG2 · KNN 7.2 Object Tracking Single Object Tracking Siamese Networks · SiamRPN · OSTrack Multi-Object Tracking SORT · DeepSORT · ByteTrack · BoT-SORT · OC-SORT Tracking Metrics MOTA · IDF1 · HOTA 7.3 Video Understanding Two-Stream Networks Spatial Stream · Temporal Stream 3D CNNs C3D · I3D · SlowFast · X3D Video Transformers TimeSformer · ViViT · VideoMAE Skeleton-Based Action Recognition ST-GCN · Graph Convolutions 7.4 Image Generation GANs DCGAN · StyleGAN · Pix2Pix · CycleGAN Autoencoders and Tokenizers VAE · VQ-VAE · VQGAN Diffusion Models DDPM · DDIM · Latent Diffusion · Diffusion Transformers Controllable Generation ControlNet · IP-Adapter · Inpainting · LoRA Generative Metrics FID · Inception Score · CLIP Score 7.5 Video Generation and Enhancement Text-to-Video Models Sora · Veo · Wan · HunyuanVideo Video Super-Resolution BasicVSR · Real-ESRGAN · Temporal Consistency Frame Interpolation RIFE · FILM · Motion Estimation 8.1 Camera Geometry and Calibration Pinhole Camera Model Intrinsics · Extrinsics · Projection Camera Calibration Checkerboard Targets · Lens Distortion · Reprojection Error Epipolar Geometry Fundamental Matrix · Essential Matrix · Triangulation 8.2 Depth Estimation Stereo Matching Disparity Maps · Block Matching · Semi-Global Matching Monocular Depth MiDaS · Depth Anything V2 · Metric Depth Depth Sensors Structured Light · Time of Flight · LiDAR 8.3 Point Clouds and 3D Data 3D Representations Point Clouds · Voxels · Meshes · SDFs Point Cloud Processing Open3D · PCL · ICP Registration Point Cloud Deep Learning PointNet · PointNet++ · KPConv · Point Transformer 3D Object Detection VoxelNet · PointPillars · SECOND · CenterPoint 8.4 Structure from Motion and SLAM Structure from Motion COLMAP · GLOMAP · Bundle Adjustment Visual SLAM ORB-SLAM3 · DSO · Loop Closure Visual-Inertial Odometry VINS-Mono · IMU Preintegration · Sensor Fusion Learned 3D Reconstruction DUSt3R · MASt3R · VGGT 8.5 Neural 3D Representations Neural Radiance Fields NeRF · Mip-NeRF · Instant NGP 3D Gaussian Splatting Rasterization · Dynamic Scenes · Mesh Extraction Image-to-3D Generation Multi-View Diffusion · Text-to-3D 9.1 Data Management Annotation Tools CVAT · Label Studio · Roboflow Dataset Versioning and Curation DVC · lakeFS · FiftyOne Active Learning Uncertainty Sampling · Human-in-the-Loop Synthetic Data Omniverse · Unity · Blender · CARLA 9.2 Model Optimization Quantization PTQ · QAT · INT8 · FP16 · FP8 Pruning and Sparsity Structured Pruning · Unstructured Pruning · 2:4 Sparsity Knowledge Distillation Teacher-Student · Feature Distillation Hardware-Aware NAS Latency Constraints · Once-for-All GPU Programming CUDA · cuDNN · Triton Kernels 9.3 Inference Runtimes and Compilers ONNX and ONNX Runtime NVIDIA TensorRT FP16 · INT8 · Layer Fusion Intel OpenVINO CPU · Integrated GPU · NPU Deep Learning Compilers torch.compile · Apache TVM · MLIR 9.4 Edge and Mobile Deployment Edge Hardware Jetson Orin · Raspberry Pi 5 · Hailo · OAK-D Mobile Runtimes LiteRT · Core ML · ExecuTorch · NCNN Web Deployment ONNX Runtime Web · WebGPU · TensorFlow.js · WebAssembly Edge Fleet Management OTA Updates · Remote Monitoring 9.5 Serving and Monitoring Containerization Docker · NVIDIA Container Toolkit Model Serving Triton Inference Server · BentoML · KServe · Ray Serve Orchestration and Pipelines Kubernetes · Kubeflow · Airflow Model Registry MLflow · SageMaker · Vertex AI Production Monitoring Data Drift · OOD Detection · Performance Metrics Cloud Vision APIs AWS Rekognition · Google Cloud Vision · Azure AI Vision 9.6 Responsible Vision AI Bias and Fairness Dataset Bias · Demographic Parity · Debiasing Privacy Preservation Face Anonymization · Federated Learning · Differential Privacy Adversarial Robustness Adversarial Attacks · Defenses · Deepfake Detection 10.1 Domain Applications Autonomous Driving and Robotics Sensor Fusion · BEV Perception · Lane Detection · Occupancy Medical Imaging DICOM · NIfTI · 3D U-Net · nnU-Net · MONAI Remote Sensing Multispectral · Hyperspectral · SAR · Geospatial Foundation Models Industrial Inspection Defect Detection · Anomaly Detection · Metrology 10.2 Capstone Projects Real-Time Detection App Custom Dataset · YOLO · Edge Deployment Segmentation Pipeline Annotation · Training · Evaluation · Serving 3D Reconstruction Project SfM · Gaussian Splatting · Visualization Vision-Language Application VLM · Visual Search · Captioning 10.3 Portfolio and Interviews Portfolio GitHub Repos · Live Demos · Technical Blog Posts Technical Interviews CV Fundamentals · Coding · ML System Design Paper Discussions Architecture Trade-offs · Recent Research Career Paths Perception Engineer · ML Engineer · Research Engineer