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

Hugging Face Daily Papers Papers
adversarial frechet-distance visual-generation post-training diffusion flow-matching

Summary

The paper introduces Adversarial Fréchet Distance (AdvFD), which adds a learnable adversarial feature space to static Fréchet losses to improve generator post-training, with real-feature whitening to stabilize optimization.

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.
Original Article
View Cached Full Text

Cached at: 08/12/26, 08:19 AM

Paper page - AdvFD: Boosting Visual Generation via Adversarial Fr’echet Distance Loss

Source: https://huggingface.co/papers/2608.11205

Abstract

Adversarial Fréchet Distance improves generator post-training by adding a learnable adversarial feature space to static Fréchet losses, with whitening to stabilize optimization.

Fréchet distancehas recently emerged as an effective distribution-level objective forgenerator post-training, complementing the conventional sample-level diffusion andflow-matching losses. However, directly optimizing Fréchet objectives can causeFréchet 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 staticpretrained feature spacesused 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 proposeAdversarial Fréchet Distance(AdvFD), which complements the static representation targets in FD-Loss with a calibratedadversarially learned representation.AdvFDaugments 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 introducereal-feature whitening, which normalizes its scale and covariance geometry and stabilizes the min--max optimization. Extensive experiments show thatAdvFDconsistently improvesone-step generatorpost-training across both JiT and pMF backbones and across different model scales.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2608\.11205

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.11205 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.11205 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.11205 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Representation Fréchet Loss for Visual Generation

Papers with Code Trending

This paper introduces FD-loss, a method to optimize Fréchet Distance as a training objective for visual generation by decoupling population and batch sizes. It demonstrates that this approach improves generator quality and suggests FID may not always accurately reflect visual quality.

Optimizing Visual Generative Models via Distribution-wise Rewards

Hugging Face Daily Papers

This paper presents a reinforcement learning framework for visual generative models that uses distribution-wise rewards, with a subset-replace strategy for efficiency, improving image diversity and quality while addressing mode collapse and reward hacking.

FedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning

arXiv cs.AI

FedOPAL proposes a framework that adapts visual prompts as feature rectifiers for one-shot federated learning, achieving efficient gradient-free aggregation via analytic methods while outperforming existing analytical approaches and matching iterative methods with zero server-side training costs.