DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915625355444224 |
|---|---|
| author | Shen, Jialiang Zheng, Jiyang Xue, Yunqi Chen, Huajie Yao, Yu Kang, Hui Liu, Ruiqi Gong, Helin Yang, Yang Wang, Dadong Liu, Tongliang |
| author_facet | Shen, Jialiang Zheng, Jiyang Xue, Yunqi Chen, Huajie Yao, Yu Kang, Hui Liu, Ruiqi Gong, Helin Yang, Yang Wang, Dadong Liu, Tongliang |
| contents | With growing concerns over image authenticity and digital safety, the field of AI-generated image (AIGI) detection has progressed rapidly. Yet, most AIGI detectors still struggle under real-world degradations, particularly motion blur, which frequently occurs in handheld photography, fast motion, and compressed video. Such blur distorts fine textures and suppresses high-frequency artifacts, causing severe performance drops in real-world settings. We address this limitation with a blur-robust AIGI detection framework based on teacher-student knowledge distillation. A high-capacity teacher (DINOv3), trained on clean (i.e., sharp) images, provides stable and semantically rich representations that serve as a reference for learning. By freezing the teacher to maintain its generalization ability, we distill its feature and logit responses from sharp images to a student trained on blurred counterparts, enabling the student to produce consistent representations under motion degradation. Extensive experiments benchmarks show that our method achieves state-of-the-art performance under both motion-blurred and clean conditions, demonstrating improved generalization and real-world applicability. Source codes will be released at: https://github.com/JiaLiangShen/Dino-Detect-for-blur-robust-AIGC-Detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12511 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection Shen, Jialiang Zheng, Jiyang Xue, Yunqi Chen, Huajie Yao, Yu Kang, Hui Liu, Ruiqi Gong, Helin Yang, Yang Wang, Dadong Liu, Tongliang Computer Vision and Pattern Recognition Machine Learning With growing concerns over image authenticity and digital safety, the field of AI-generated image (AIGI) detection has progressed rapidly. Yet, most AIGI detectors still struggle under real-world degradations, particularly motion blur, which frequently occurs in handheld photography, fast motion, and compressed video. Such blur distorts fine textures and suppresses high-frequency artifacts, causing severe performance drops in real-world settings. We address this limitation with a blur-robust AIGI detection framework based on teacher-student knowledge distillation. A high-capacity teacher (DINOv3), trained on clean (i.e., sharp) images, provides stable and semantically rich representations that serve as a reference for learning. By freezing the teacher to maintain its generalization ability, we distill its feature and logit responses from sharp images to a student trained on blurred counterparts, enabling the student to produce consistent representations under motion degradation. Extensive experiments benchmarks show that our method achieves state-of-the-art performance under both motion-blurred and clean conditions, demonstrating improved generalization and real-world applicability. Source codes will be released at: https://github.com/JiaLiangShen/Dino-Detect-for-blur-robust-AIGC-Detection. |
| title | DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2511.12511 |