| title | Representation Fréchet Loss for Visual Generation |
|---|---|
| authors | Jiawei Yang, Zhengyang Geng, Xuan Ju, Yonglong Tian, Yue Wang |
| date | 2026-04-30 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2604.28190 |
| upvotes | 29 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | We show that Fréchet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation space. Our idea is simple: decouple the population size for FD estimation (e.g., 50k) from the batch size for gradient computation (e.g., 1024). We term this approach FD-loss. Optimizing FD-loss reveals several surprising findings. First, post-training a base generator with FD-loss in different representation spaces consistently improves visual quality. Under the Inception feature space, a one-step generator achieves0.72 FID on ImageNet 256x256. Second, the same FD-loss repurposes multi-step generators into strong one-step generators without teacher distillation, adversarial training or per-sample targets. Third, FID can misrank visual quality: modern representations can yield better samples despite worse Inception FID. This motivates FDr^k, a multi-representation metric. We hope this work will encourage further exploration of distributional distances in diverse representation spaces as both training objectives and evaluation metrics for generative models. |
cite
@misc{yang2026representation,
title={Representation Fréchet Loss for Visual Generation},
author={Jiawei Yang and Zhengyang Geng and Xuan Ju and Yonglong Tian and Yue Wang},
year={2026},
eprint={2604.28190},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2604.28190}
}