HRR: Hierarchical Retrospection Refinement for Generated Image Detection

TL;DR

This paper introduces HRR, a diffusion model-based framework for detecting generated images that enhances multi-scale feature representation and reduces style bias, leading to superior detection performance.

Contribution

The paper proposes a novel hierarchical retrospection refinement framework that improves generalization in generated image detection by multi-scale style analysis and feature refinement.

Findings

HRR outperforms state-of-the-art methods in detection accuracy.

The multi-scale style retrospection module enhances realistic feature extraction.

The feature refinement module reduces redundancy and improves generalization.

Abstract

Generative artificial intelligence holds significant potential for abuse, and generative image detection has become a key focus of research. However, existing methods primarily focused on detecting a specific generative model and emphasizing the localization of synthetic regions, while neglecting the interference caused by image size and style on model learning. Our goal is to reach a fundamental conclusion: Is the image real or generated? To this end, we propose a diffusion model-based generative image detection framework termed Hierarchical Retrospection Refinement~(HRR). It designs a multi-scale style retrospection module that encourages the model to generate detailed and realistic multi-scale representations, while alleviating the learning biases introduced by dataset styles and generative models. Additionally, based on the principle of correntropy sparse additive machine, a feature refinement module is designed to reduce the impact of redundant features on learning and capture the intrinsic structure and patterns of the data, thereby improving the model's generalization ability. Extensive experiments demonstrate the HRR framework consistently delivers significant performance improvements, outperforming state-of-the-art methods in generated image detection task.