# Backpropagating through Fr'echet Inception Distance

arXiv: https://arxiv.org/abs/2009.14075 · HTML: https://mlsanity.com/paper/2009.14075/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2020.

## Built on by (most cited first, 2 of 2)

- [High Perceptual Quality Image Denoising with a Posterior Sampling CGAN](https://mlsanity.com/paper/2103.04192/) (2021)
- [Data Augmentation For Medical MR Image Using Generative Adversarial Networks](https://mlsanity.com/paper/2111.14297/) (2021)

## Abstract (arXiv)

The Fr'echet Inception Distance (FID) has been used to evaluate hundreds of generative models. We introduce FastFID, which can efficiently train generative models with FID as a loss function. Using FID as an additional loss for Generative Adversarial Networks improves their FID.