Diversity over Uniformity: Rethinking Representation in Generated Image Detection

2026-02-28

AI Summary

Existing methods for detecting generated images often exhibit limited generalization to unseen generative models due to their overreliance on a few salient forgery cues. To address this issue, this work proposes an anti-feature-collapse learning framework that preserves diverse and complementary discriminative evidence by filtering out task-irrelevant components, suppressing excessive overlap of forgery cues in the representation space, and incorporating a multi-view discrimination mechanism. This approach effectively prevents discriminative information from collapsing into dominant feature directions. Extensive experiments demonstrate that the proposed method significantly outperforms state-of-the-art techniques across multiple public benchmarks, achieving a 5.02% improvement in accuracy under cross-model detection scenarios, thereby exhibiting superior generalization capability and detection stability.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

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.

Problem

• generated image detection
• generalization
• forgery cues
• representation diversity
• visual forensics

Innovation

• anti-feature-collapse
• diverse representation
• generated image detection
• forgery cues
• generalization