Anchor-Regularized Adaptation for Generalizable AI-Generated Image Detection with DINOv3

[2608.15196] Anchor-Regularized Adaptation for Generalizable AI-Generated Image Detection with DINOv3 Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2608.15196 (cs) [Submitted on 15 Aug 2026] Title: Anchor-Regularized Adaptation for Generalizable AI-Generated Image Detection with DINOv3 Authors: Hyeongjun Choi , Juhun Lee , Davide Cozzolino , Luisa Verdoliva , Simon S. Woo View a PDF of the paper titled Anchor-Regularized Adaptation for Generalizable AI-Generated Image Detection with DINOv3, by Hyeongjun Choi and 4 other authors View PDF HTML (experimental) Abstract: Recent works in AI-generated image detection have shown that careful training data alignment can improve generalization by removing spurious correlations. However, linear probes on frozen DINOv3 representations achieve remarkably strong performance even when trained on misaligned datasets. Motivated by this result, we analyze the underlying rationale and the limits of this generalization. We find that frozen DINOv3 performs well because its decisions rely on features that faithfully represent the space of authentic images. At the same time, its final layer is less effective at capturing the subtle pixel-artifact cues that can be emphasized by aligned training data. We further observe that naively mixing aligned and misaligned data during adaptation improves sensitivity to such cues but at the cost of distorting the pre-trained representation, limiting generalization. To address this issue, we propose Anchor-Regularized Adaptation (ARA). We apply Low-Rank Adaptation to capture pixel-level artifacts while leveraging a frozen anchor classifier to avoid deviations from the original representation structure. This allows the model to exploit pixel-artifact cues without sacrificing generalization. Our method achieves state-of-the-art performance on nine diverse and challenging benchmarks, indicating that ARA enables complementary supervision from misaligned and aligned data for more effective detection. Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.15196 [cs.CV] (or arXiv:2608.15196v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.15196 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Hyeongjun Choi [ view email ] [v1] Sat, 15 Aug 2026 12:26:28 UTC (6,490 KB) Full-text links: Access Paper: View a PDF of the paper titled Anchor-Regularized Adaptation for Generalizable AI-Generated Image Detection with DINOv3, by Hyeongjun Choi and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Anchor-Regularized Adaptation for Generalizable AI-Generated Image Detection with DINOv3#611142
• Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification under Foundation-Model Pretraining#1052248
• DIFTA-3D: Depth-Consistent Instance-Level Feature Transfer and Adaptation of DINOv3 for 3D Detection#1062588
• Combining General and Domain-Specific Pretext Tasks for Brain MR Image Segmentation#1105267
• In-Context Multiple Instance Learning#986269