Metraipolis › archive › dc_ef0866cf2ec0

Out-of-distribution AI-generated image detection with zero-phase deconvolution for residual whitening — arXiv:2611.00043

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00043
License (as archived): CC0-1.0
Archived: 2026-11-03T10:45:38.413Z
SHA-256 of the archived text: d1c70f5f986f91ca19bff1bcd25847ebb1dd812720bbde3626532363bad50be2
Stable URL of this page: https://metraipolis.com/documento/dc_ef0866cf2ec0

How to cite

Out-of-distribution AI-generated image detection with zero-phase deconvolution for residual whitening — arXiv:2611.00043 — arXiv (en), https://arxiv.org/abs/2611.00043 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef0866cf2ec0 (Metraipolis archive dc_ef0866cf2ec0, sha256 d1c70f5f986f91ca19bff1bcd25847ebb1dd812720bbde3626532363bad50be2)

BibTeX

@misc{dcef0866cf2ec0,
  title = {Out-of-distribution AI-generated image detection with zero-phase deconvolution for residual whitening — arXiv:2611.00043},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00043},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef0866cf2ec0; sha256 d1c70f5f986f91ca19bff1bcd25847ebb1dd812720bbde3626532363bad50be2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00043. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Current AI-generated image detection methods struggle in out-of-distribution testing conditions because detectors are usually not robust when evaluated on generators not included in the training set. This work explores a way to mitigate the forensic bias between sources of images -whether real or generated -by removing generator-specific fingerprints. This new training process can be approximated by pre-processing involving a deconvolution operation designed to remove correlated noise patterns inducing loss of generalization. Indeed, we show that whitening the spatial distribution of the image noise residuals can significantly improve the performance of detectors on images coming from generators unseen during training. In particular, an end-to-end CNN model trained on whitened image residuals improves detection by 12.6% on average compared to a training involving original images.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2611.00043 — 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 2026-11-03T10:39:50.369Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).