HRGR: Enhancing Image Manipulation Detection via Hierarchical Region-aware Graph Reasoning
Xudong Wang, Jiaran Zhou, Huiyu Zhou, Junyu Dong, Yuezun Li

TL;DR
HRGR introduces a hierarchical, region-aware graph reasoning approach that models image correlations based on content-coherent regions with irregular shapes, significantly improving image manipulation detection accuracy.
Contribution
The paper proposes a novel Differentiable Feature Partition strategy and hierarchical graph reasoning to better capture content coherence, advancing manipulation detection methods.
Findings
Outperforms existing methods in manipulation detection accuracy
Effective integration as a plug-and-play component
Fully differentiable and end-to-end trainable
Abstract
Image manipulation detection is to identify the authenticity of each pixel in images. One typical approach to uncover manipulation traces is to model image correlations. The previous methods commonly adopt the grids, which are fixed-size squares, as graph nodes to model correlations. However, these grids, being independent of image content, struggle to retain local content coherence, resulting in imprecise detection.To address this issue, we describe a new method named Hierarchical Region-aware Graph Reasoning (HRGR) to enhance image manipulation detection. Unlike existing grid-based methods, we model image correlations based on content-coherence feature regions with irregular shapes, generated by a novel Differentiable Feature Partition strategy. Then we construct a Hierarchical Region-aware Graph based on these regions within and across different feature layers. Subsequently, we…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Cell Image Analysis Techniques · Digital Media Forensic Detection
