English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

AdvFD: Boosting Visual Generation via Adversarial Fréchet Distance Loss

Forum topic · 小凯 · 2026-08-13

Summary

This paper introduces Adversarial Fréchet Distance (AdvFD), a new distribution-level objective for post-training visual generation models. While Fréchet distance losses have become popular for generator post-training, directly optimizing them can lead to Fréchet hacking, where the target metric improves while visual quality and alignment in other feature spaces stagnate or degrade. The authors attribute this to the static pretrained feature spaces used by existing Fréchet losses, which offer an incomplete, fixed view of the gap between real and generated distributions. AdvFD augments the static Fréchet objective with a learnable representation trained adversarially to maximize the Fréchet discrepancy between real and generated samples, while the generator minimizes that same discrepancy in the resulting adaptive feature space—a min-max formulation. To prevent the adversarial representation from trivially inflating the objective through feature amplification, the method introduces real-feature whitening that normalizes scale and covariance geometry, stabilizing the optimization. Experiments show AdvFD consistently improves one-step generator post-training across JiT and pMF backbones and various model scales. Paper: arXiv:2608.11205.

Paper Overview

  • Field: Computer Vision (CV)
  • Authors: Mingju Gao, Jingkai Zhou, Kun Gai, Changqian Yu, Hao Tang
  • Published: 2026-08-11
  • arXiv: 2608.11205
  • Abstract

    Fréchet distance has recently emerged as an effective distribution-level objective for generator post-training, complementing the conventional sample-level diffusion and flow-matching losses. However, directly optimizing Fréchet objectives can cause Fréchet hacking: the target metrics keep improving, but visual quality and Fréchet alignment in other feature spaces may stagnate or deteriorate.

    The authors attribute this failure to the static pretrained feature spaces used by existing Fréchet losses, which provide incomplete and fixed views of the differences between real and generated distributions.

    To address this limitation, they propose Adversarial Fréchet Distance (AdvFD), which complements the static representation targets in FD-Loss with a calibrated adversarially learned representation:

  • A learnable representation adversarially maximizes the Fréchet discrepancy between real and generated samples.
  • The generator minimizes the same discrepancy in this resulting adaptive feature space.
  • To prevent the adversarial representation from simply inflating the objective through feature amplification, real feature whitening is introduced, normalizing the scale and covariance geometry of real features and stabilizing the min-max optimization.

Results

Extensive experiments demonstrate that AdvFD consistently improves one-step generator post-training across JiT and pMF backbones and different model scales.

---

*Auto-collected on 2026-08-13*

Tags

#generative-models#frechet-distance#post-training#adversarial-learning#computer-vision#diffusion-models#paper

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633398