Metraipolis › archive › dc_31ff87aa8bfd

Look Closer: Patch-wise Supervision for AI-Generated Image Detection — arXiv:2609.37937

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37937
License (as archived)
CC0-1.0
Archived
2026-10-07T18:41:36.491Z
SHA-256 of the archived text
fe9e9827b4338a24d4bbe72c37fd541f18d508e955c5ab6a8daf5f189cb037cb
Stable URL of this page
https://metraipolis.com/documento/dc_31ff87aa8bfd

How to cite

Look Closer: Patch-wise Supervision for AI-Generated Image Detection — arXiv:2609.37937 — arXiv (en), https://arxiv.org/abs/2609.37937 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31ff87aa8bfd (Metraipolis archive dc_31ff87aa8bfd, sha256 fe9e9827b4338a24d4bbe72c37fd541f18d508e955c5ab6a8daf5f189cb037cb)
BibTeX
@misc{dc31ff87aa8bfd,
  title = {Look Closer: Patch-wise Supervision for AI-Generated Image Detection — arXiv:2609.37937},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37937},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31ff87aa8bfd; sha256 fe9e9827b4338a24d4bbe72c37fd541f18d508e955c5ab6a8daf5f189cb037cb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37937. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

How much of an image does a detector need to see? Small RGB regions can retain useful evidence of image synthesis even when they reveal little of the full scene. Motivated by single-patch detection, we study patch-wise supervision: a shared backbone classifies explicit crops, each crop receives its own loss, and patch probabilities are averaged only at inference. The procedure requires neither handcrafted residual filtering nor a learned image-level fusion module. Experiments span single-patch selection, multiple generator collections, and four CNN and Transformer backbones. On GenImage, the reported patch-wise variants improve average accuracy over their whole-image counterparts across all four backbones. Comparisons of supervision granularity, source resolution, crop size, and inference coverage further characterize the approach, while post-processing tests and difficult-image evaluation reveal its limitations. The historical experiments include evaluation-based model selection, so their scores are not presented as a uniformly selected leaderboard comparison. Overall, the study identifies explicit local input and patch-level supervision as a simple, useful combination for investigating generalizable AI-generated image detection.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.37937 — 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 2026-10-07T18:04:24.923Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).