Fréchet Distance
A mathematical measure used to calculate the similarity between two curves, frequently applied to evaluate the quality of images produced by generative models.
Think of It Like This
Like measuring the shortest leash needed for a person walking on one path to walk a dog on a separate path without either of them moving backward.
In machine learning, the Fréchet Inception Distance (FID) uses this concept to evaluate generative models like GANs and diffusion models. It calculates the Fréchet distance between the feature distributions of real and generated images in the latent space of a pre-trained network. A lower FID score indicates that the generated images are highly realistic and diverse.