发表机构
Peking University; KlingAI（北京大学; 可灵AI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出AdvFD算法，通过补充静态Fréchet损失的对抗学习表示并引入真实特征白化，解决Fréchet攻击问题，提升了JiT、pMF等骨干网络的单步生成器后训练性能。
AI 中文摘要
Fréchet距离近来已成为一种有效的分布级生成器后训练目标，可补充传统的样本级扩散和流匹配损失。然而，直接优化Fréchet目标会导致Fréchet攻击：目标指标持续提升，但视觉质量和其他特征空间中的Fréchet对齐可能停滞或恶化。我们将该失败归因于现有Fréchet损失使用的静态预训练特征空间，这些空间仅提供真实与生成分布差异的不完整且固定的视图。为解决此局限，我们提出对抗性Fréchet距离（AdvFD），它用经校准的对抗学习表示补充FD-Loss中的静态表示目标。AdvFD在原始静态Fréchet目标基础上增加了可学习表示，该表示会以对抗方式最大化真实与生成样本间的Fréchet差异，而生成器则在所得自适应特征空间中最小化该差异。为防止对抗表示通过特征放大 trivial 地增大目标，我们进一步引入真实特征白化，它对其尺度和协方差几何进行归一化，以稳定极小极大优化。大量实验表明，AdvFD在JiT和pMF两种骨干网络及不同模型规模下，均能持续改进单步生成器后训练。
英文摘要
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. We attribute this failure to the static pretrained feature spaces used by existing Fréchet losses. These feature spaces provide incomplete and fixed views of the differences between real and generated distributions. To address this limitation, we propose Adversarial Fréchet Distance (AdvFD), which complements the static representation targets in FD-Loss with a calibrated adversarially learned representation. AdvFD augments the original static Fréchet objective with a learnable representation that adversarially maximizes the Fréchet discrepancy between real and generated samples, while the generator minimizes the same discrepancy in the resulting adaptive feature space. To prevent the adversarial representation from trivially increasing the objective through feature amplification, we further introduce real-feature whitening, which normalizes its scale and covariance geometry and stabilizes the min--max optimization. Extensive experiments show that AdvFD consistently improves one-step generator post-training across both JiT and pMF backbones and across different model scales.
CommentsProject Page: https://gasaiyu.github.io/AdvFD-page/
