Diversity over Uniformity: Rethinking Representation in Generated Image Detection
This work addresses the challenge of detecting AI-generated images for visual forensics, offering an incremental improvement over existing methods by enhancing generalization to unseen generative mechanisms.
The paper tackles the problem of generated image detection by addressing the limitation of existing methods that rely on a small subset of forgery cues, which hinders generalization to unseen generative models. The proposed anti-feature-collapse learning framework improves cross-model detection accuracy by 5.02% and enhances robustness and reliability.
With the rapid advancement of generative models, generated image detection has become an important task in visual forensics. Although existing methods have achieved remarkable progress, they often rely, after training, on only a small subset of highly salient forgery cues, which limits their ability to generalize to unseen generative mechanisms. We argue that reliably generated image detection should not depend on a single decision path but should preserve multiple judgment perspectives, enabling the model to understand the differences between real and generated images from diverse viewpoints. Based on this idea, we propose an anti-feature-collapse learning framework that filters task-irrelevant components and suppresses excessive overlap among different forgery cues in the representation space, preventing discriminative information from collapsing into a few dominant feature directions. This design maintains diverse and complementary evidence within the model, reduces reliance on a small set of salient cues, and enhances robustness under unseen generative settings. Extensive experiments on multiple public benchmarks demonstrate that the proposed method significantly outperforms the state-of-the-art approaches in cross-model scenarios, achieving an accuracy improvement of 5.02% and exhibiting superior generalization and detection reliability. The source code is available at https://github.com/Yanmou-Hui/DoU.