Metraipolis › archive › dc_35fcdd39faa0

PAPT++: Risk-Aware Adversarial Tuning and Generation for Single Domain Generalization — arXiv:2609.04837

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.04837
License (as archived): CC0-1.0
Archived: 2026-10-16T23:41:12.301Z
SHA-256 of the archived text: f5e432340983cf893e7ce5d950e249f6257e0f3505cb6da540552f31848b5503
Stable URL of this page: https://metraipolis.com/documento/dc_35fcdd39faa0

How to cite

PAPT++: Risk-Aware Adversarial Tuning and Generation for Single Domain Generalization — arXiv:2609.04837 — arXiv (en), https://arxiv.org/abs/2609.04837 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_35fcdd39faa0 (Metraipolis archive dc_35fcdd39faa0, sha256 f5e432340983cf893e7ce5d950e249f6257e0f3505cb6da540552f31848b5503)

BibTeX

@misc{dc35fcdd39faa0,
  title = {PAPT++: Risk-Aware Adversarial Tuning and Generation for Single Domain Generalization — arXiv:2609.04837},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04837},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_35fcdd39faa0; sha256 f5e432340983cf893e7ce5d950e249f6257e0f3505cb6da540552f31848b5503},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04837. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Single domain generalization (SDG) aims to learn a model from one labeled source domain that generalizes to unseen target domains. A common strategy is to enrich the source distribution with augmented or generated samples, and recent text-to-image (T2I) diffusion models provide a strong generative prior for this purpose. However, diversity alone is insufficient for robust generalization, because useful generated samples should also capture variations that the current classifier finds difficult. Motivated by distributionally robust optimization (DRO), we define a semantic ambiguity set in the class-conditional generative space of a pretrained T2I model and search it for samples with high classification loss under the current classifier. To this end, we introduce PAPT++, a risk-aware adversarial generation-training framework for SDG. PAPT++ first learns diverse semantic reference images for each class through image-text alignment and intra-class diversity regularization. These references then serve as denoising targets during classifier-guided diffusion synthesis, reducing semantic drift while guiding generation toward challenging variations. The generated samples are combined with the source data to update the classifier, and the updated classifier guides the next synthesis round in return. In this way, PAPT++ progressively exposes the classifier to challenging yet semantically consistent variations. Extensive experiments on standard SDG benchmarks demonstrate the superiority of the proposed PAPT++ method and the effectiveness of its main components.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.04837 — 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 2026-10-16T23:16:11.414Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).