FUSE: Unifying Spectral and Semantic Cues for Robust AI-Generated Image Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908731972780032 |
|---|---|
| author | Hossain, Md. Zahid Samu, Most. Sharmin Sultana Bhuiyan, Md. Kamrozzaman Zaman, Farhad Uz Islam, Md. Rakibul |
| author_facet | Hossain, Md. Zahid Samu, Most. Sharmin Sultana Bhuiyan, Md. Kamrozzaman Zaman, Farhad Uz Islam, Md. Rakibul |
| contents | The fast evolution of generative models has heightened the demand for reliable detection of AI-generated images. To tackle this challenge, we introduce FUSE, a hybrid system that combines spectral features extracted through Fast Fourier Transform with semantic features obtained from the CLIP's Vision encoder. The features are fused into a joint representation and trained progressively in two stages. Evaluations on GenImage, WildFake, DiTFake, GPT-ImgEval and Chameleon datasets demonstrate strong generalization across multiple generators. Our FUSE (Stage 1) model demonstrates state-of-the-art results on the Chameleon benchmark. It also attains 91.36% mean accuracy on the GenImage dataset, 88.71% accuracy across all tested generators, and a mean Average Precision of 94.96%. Stage 2 training further improves performance for most generators. Unlike existing methods, which often perform poorly on high-fidelity images in Chameleon, our approach maintains robustness across diverse generators. These findings highlight the benefits of integrating spectral and semantic features for generalized detection of images generated by AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_21695 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FUSE: Unifying Spectral and Semantic Cues for Robust AI-Generated Image Detection Hossain, Md. Zahid Samu, Most. Sharmin Sultana Bhuiyan, Md. Kamrozzaman Zaman, Farhad Uz Islam, Md. Rakibul Computer Vision and Pattern Recognition The fast evolution of generative models has heightened the demand for reliable detection of AI-generated images. To tackle this challenge, we introduce FUSE, a hybrid system that combines spectral features extracted through Fast Fourier Transform with semantic features obtained from the CLIP's Vision encoder. The features are fused into a joint representation and trained progressively in two stages. Evaluations on GenImage, WildFake, DiTFake, GPT-ImgEval and Chameleon datasets demonstrate strong generalization across multiple generators. Our FUSE (Stage 1) model demonstrates state-of-the-art results on the Chameleon benchmark. It also attains 91.36% mean accuracy on the GenImage dataset, 88.71% accuracy across all tested generators, and a mean Average Precision of 94.96%. Stage 2 training further improves performance for most generators. Unlike existing methods, which often perform poorly on high-fidelity images in Chameleon, our approach maintains robustness across diverse generators. These findings highlight the benefits of integrating spectral and semantic features for generalized detection of images generated by AI. |
| title | FUSE: Unifying Spectral and Semantic Cues for Robust AI-Generated Image Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.21695 |