Metraipolis › archive › dc_790b36618928

Beyond the Last Layer: Global Inter-Layer Aggregation for AI-Generated Image Detection — arXiv:2611.00017

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00017
License (as archived)
CC0-1.0
Archived
2026-11-03T18:15:48.353Z
SHA-256 of the archived text
a43d25a1caf8bc27dfe5de58f5bcd0e80b9f72f49986af8f86a40dbd5fbc6a15
Stable URL of this page
https://metraipolis.com/documento/dc_790b36618928

How to cite

Beyond the Last Layer: Global Inter-Layer Aggregation for AI-Generated Image Detection — arXiv:2611.00017 — arXiv (en), https://arxiv.org/abs/2611.00017 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_790b36618928 (Metraipolis archive dc_790b36618928, sha256 a43d25a1caf8bc27dfe5de58f5bcd0e80b9f72f49986af8f86a40dbd5fbc6a15)
BibTeX
@misc{dc790b36618928,
  title = {Beyond the Last Layer: Global Inter-Layer Aggregation for AI-Generated Image Detection — arXiv:2611.00017},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00017},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_790b36618928; sha256 a43d25a1caf8bc27dfe5de58f5bcd0e80b9f72f49986af8f86a40dbd5fbc6a15},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00017. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The rapid development of generative models has made AI-generated images increasingly close to real images. It has also brought several challenges to detectors, including rapid generator updates, large changes in data distribution, and limited cross-dataset generalization. Many existing methods based on pretrained vision encoders primarily use the global representation from the last layer, potentially leaving useful information from intermediate layers underexplored. To address this issue, we propose Global Inter-Layer Aggregation (GILA). GILA extracts global representations from different depths of a frozen encoder, models interactions among layer representations through inter-layer self-attention, and adaptively aggregates the resulting contextualized representations. The method is not tied to a single pretraining objective and does not require fine-tuning the pretrained encoder. We evaluated GILA on three vision backbones with different pretraining objectives, ten seen generators, and three external datasets. The experimental results show that GILA makes better use of multi-layer information in pretrained encoders and improves detection performance and cross-dataset generalization.

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).
Pagina del lavoro: https://arxiv.org/abs/2611.00017 — 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 2026-11-03T18:09:53.469Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).