AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss

• 类型：arxiv
• 标识：2608.11205
• 链接：https://arxiv.org/abs/2608.11205
• 主分类：engineering
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：Adversarial Fr\'echet Distance (AdvFD), which complements the static representation targets in FD-Loss with a calibrated adversarially learned representation that adversarially maximizes the Fr\'echet discrepancy between real and generated samples, and introduces real-feature whitening, which normalizes its scale and covariance geometry and stabilizes the min--max optimization.
• 待LLM分类：否
• 标题中文：AdvFD：通过对抗 Fréchet 距离损失提升视觉生成
• TLDR中文：对抗性 Fréchet 距离 (AdvFD) 用经过校准的对抗性学习表示来补充 FD-Loss 中的静态表示目标，通过对抗方式最大化真实样本与生成样本之间的 Fréchet 差异；同时引入真实特征白化，对尺度与协方差几何进行归一化，从而稳定极小极大优化。
• 来源文件：
• /inbox/tom/_candidates/2026-08-12-agent-rag-longcontext-candidates.json
• [S2 enrich]