4 papers
IncreFA: Breaking the Static Wall of Generative Model Attribution
Haotian Qin, Dongliang Chang, Yueying Gao +3
As AI generative models evolve at unprecedented speed, image attribution has become a moving target. New diffusion, adversarial and autoregressive generators appear almost monthly,…
Toward Generalizable Forgery Detection and Reasoning
Yueying Gao, Dongliang Chang, Bingyao Yu +5
Accurate and interpretable detection of AI-generated images is essential for mitigating risks associated with AI misuse. However, the substantial domain gap among generative models…
Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportions
Jinyi Chang, Dongliang Chang, Lei Chen +2
In recent years, Fine-Grained Visual Classification (FGVC) has achieved impressive recognition accuracy, despite minimal inter-class variations. However, existing methods heavily r…
Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection
Haotian Qin, Dongliang Chang, Yueying Gao +3
Although existing CLIP-based methods for detecting AI-generated images have achieved promising results, they are still limited by severe feature redundancy, which hinders their gen…