The Fréchet Inception Distance (FID) is a metric used to evaluate the quality of images generated by generative models, particularly in the context of deep learning and computer vision. It is commonly employed to assess the performance of Generative Adversarial Networks (GANs) and other image synthesis techniques.
FID calculates the distance between two probability distributions: one representing the generated images and the other representing real images from a dataset. To compute FID, the images are first passed through a pre-trained Inception v3 neural network, which extracts feature representations of the images. These features are then modeled as multivariate Gaussian distributions, characterized by their mean and covariance.
The FID score is computed using the Fréchet distance, which quantifies how far apart these two distributions are. A lower FID score indicates that the generated images are more similar to the real images, suggesting better quality and diversity in the outputs of the generative model. Conversely, a higher FID score indicates poorer quality and greater divergence from real images.
Overall, FID serves as a robust evaluation metric, allowing researchers and practitioners to compare various generative models effectively. It has become a standard benchmark in the field of generative modeling, helping to advance the development of high-quality image synthesis techniques.