HRGR: Enhancing Image Manipulation Detection via Hierarchical Region-aware Graph Reasoning

2024-10-29

arXiv.org

AI Summary

Existing image manipulation detection methods predominantly rely on fixed-grid representations to model pixel relationships, neglecting semantic content structure—leading to poor local consistency and inaccurate localization. To address this, we propose a content-aware hierarchical region graph modeling framework. First, we design a differentiable feature partitioning strategy that generates semantically adaptive, irregular region nodes. Second, we construct a cross-layer, multi-scale region graph and employ a topology-agnostic graph neural network for robust reasoning. The entire pipeline is end-to-end differentiable and requires no auxiliary supervision. Our method achieves significant improvements over grid-based baselines across multiple mainstream benchmarks (e.g., CASIA, COVERAGE, Columbia), demonstrating strong generalization and plug-and-play compatibility. Code and pre-trained models are publicly available.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

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 describe a structural-agnostic graph reasoning strategy tailored for our graph to enhance the representation of nodes. Our method is fully differentiable and can seamlessly integrate into mainstream networks in an end-to-end manner, without requiring additional supervision. Extensive experiments demonstrate the effectiveness of our method in image manipulation detection, exhibiting its great potential as a plug-and-play component for existing architectures. Codes and models are available at https://github.com/OUC-VAS/HRGR-IMD.

Problem

• Detect image manipulation via content-coherent regions
• Model correlations using irregular feature regions
• Enhance detection with hierarchical graph reasoning

Innovation

• Uses content-coherence feature regions
• Constructs Hierarchical Region-aware Graph
• Implements structural-agnostic graph reasoning