Metraipolis › archive › dc_6f326e6ea52b
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
- 2026-11-03T10:54:45.336Z
- SHA-256 of the archived text
51adc4336476213a2a9dcdc273722addcb9c1b2d569c0d3d2104ec1a167c0e57- Stable URL of this page
https://metraipolis.com/documento/dc_6f326e6ea52b
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_6f326e6ea52b (Metraipolis archive dc_6f326e6ea52b, sha256 51adc4336476213a2a9dcdc273722addcb9c1b2d569c0d3d2104ec1a167c0e57)
BibTeX
@misc{dc6f326e6ea52b,
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_6f326e6ea52b; sha256 51adc4336476213a2a9dcdc273722addcb9c1b2d569c0d3d2104ec1a167c0e57},
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 2026-11-03T10:49:38.446Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).