Diversity Matters: Dataset Diversification and Dual-Branch Network for Generalized AI-Generated Image Detection
For digital security and misinformation detection, this work provides a more robust detector against diverse generative models, though the gains are incremental over prior art.
The paper tackles generalized AI-generated image detection by proposing a framework that uses feature-domain similarity filtering to diversify training data and a dual-branch network combining CLIP features from pixel and frequency domains. The method achieves significant improvements in cross-model and cross-dataset performance over existing methods.
The rapid proliferation of AI-generated images, powered by generative adversarial networks (GANs), diffusion models, and other synthesis techniques, has raised serious concerns about misinformation, copyright violations, and digital security. However, detecting such images in a generalized and robust manner remains a major challenge due to the vast diversity of generative models and data distributions. In this work, we present \textbf{Diversity Matters}, a novel framework that emphasizes data diversity and feature domain complementarity for AI-generated image detection. The proposed method introduces a feature-domain similarity filtering mechanism that discards redundant or highly similar samples across both inter-class and intra-class distributions, ensuring a more diverse and representative training set. Furthermore, we propose a dual-branch network that combines CLIP features from the pixel domain and the frequency domain to jointly capture semantic and structural cues, leading to improved generalization against unseen generative models and adversarial conditions. Extensive experiments on benchmark datasets demonstrate that the proposed approach significantly improves cross-model and cross-dataset performance compared to existing methods. \textbf{Diversity Matters} highlights the critical role of data and feature diversity in building reliable and robust detectors against the rapidly evolving landscape of synthetic content.