Metraipolis › archive › dc_7e94f033af02

AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss — arXiv:2608.11205

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11205
License (as archived)
CC0-1.0
Archived
2026-10-19T06:30:43.105Z
SHA-256 of the archived text
a027d1ea1c7788f4ce3809c1970dc1fa806260d9b0bccea3d99a893b3c6e9995
Stable URL of this page
https://metraipolis.com/documento/dc_7e94f033af02

How to cite

AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss — arXiv:2608.11205 — arXiv (en), https://arxiv.org/abs/2608.11205 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e94f033af02 (Metraipolis archive dc_7e94f033af02, sha256 a027d1ea1c7788f4ce3809c1970dc1fa806260d9b0bccea3d99a893b3c6e9995)
BibTeX
@misc{dc7e94f033af02,
  title = {AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss — arXiv:2608.11205},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11205},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e94f033af02; sha256 a027d1ea1c7788f4ce3809c1970dc1fa806260d9b0bccea3d99a893b3c6e9995},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11205. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.11205 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T06:25:27.328Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).