Leveraging Arbitrary Data Sources for AI-Generated Image Detection Without Sacrificing Generalization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911547840790528 |
|---|---|
| author | He, Qinghui Zhang, Haifeng Bi, Xiuli Liu, Bo Pun, Chi-Man Xiao, Bin |
| author_facet | He, Qinghui Zhang, Haifeng Bi, Xiuli Liu, Bo Pun, Chi-Man Xiao, Bin |
| contents | The accelerating advancement of generative models has introduced new challenges for detecting AI-generated images, especially in real-world scenarios where novel generation techniques emerge rapidly. Existing learning paradigms are likely to make classifiers data-dependent, resulting in narrow decision margins and, consequently, limited generalization ability to unseen generative models. We observe that both real and generated images intend to form clustered low-dimensional manifolds within high-level feature spaces extracted by pre-trained visual encoders. Building on this observation, we propose a single-class attribution modeling framework that first amplifies the intrinsic differences between real and generated images by constructing a compact attribution space from any single-class training set, either composed of real images or generated ones, and then establishes a more stable decision boundary upon the enlarged separation. This process enhances class distinction and mitigates the reliance on generator-specific artifacts, thereby improving cross-model generalization. Extensive experiments show that our method generalizes well across various unseen generative models, outperforming existing detectors by as much as 7.21% in accuracy and 7.20% in cross-model generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00717 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Leveraging Arbitrary Data Sources for AI-Generated Image Detection Without Sacrificing Generalization He, Qinghui Zhang, Haifeng Bi, Xiuli Liu, Bo Pun, Chi-Man Xiao, Bin Computer Vision and Pattern Recognition The accelerating advancement of generative models has introduced new challenges for detecting AI-generated images, especially in real-world scenarios where novel generation techniques emerge rapidly. Existing learning paradigms are likely to make classifiers data-dependent, resulting in narrow decision margins and, consequently, limited generalization ability to unseen generative models. We observe that both real and generated images intend to form clustered low-dimensional manifolds within high-level feature spaces extracted by pre-trained visual encoders. Building on this observation, we propose a single-class attribution modeling framework that first amplifies the intrinsic differences between real and generated images by constructing a compact attribution space from any single-class training set, either composed of real images or generated ones, and then establishes a more stable decision boundary upon the enlarged separation. This process enhances class distinction and mitigates the reliance on generator-specific artifacts, thereby improving cross-model generalization. Extensive experiments show that our method generalizes well across various unseen generative models, outperforming existing detectors by as much as 7.21% in accuracy and 7.20% in cross-model generalization. |
| title | Leveraging Arbitrary Data Sources for AI-Generated Image Detection Without Sacrificing Generalization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.00717 |