DRRNet: Macro-Micro Feature Fusion and Dual Reverse Refinement for Camouflaged Object Detection

TL;DR

DRRNet introduces a four-stage macro-micro feature fusion and dual reverse refinement approach to improve camouflaged object detection by effectively capturing global and local features and refining object boundaries.

Contribution

The paper presents a novel four-stage architecture with dual feature fusion and reverse refinement modules specifically designed for camouflaged object detection.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effectively suppresses background interference

Enhances object boundary continuity

Abstract

The core challenge in Camouflage Object Detection (COD) lies in the indistinguishable similarity between targets and backgrounds in terms of color, texture, and shape. This causes existing methods to either lose edge details (such as hair-like fine structures) due to over-reliance on global semantic information or be disturbed by similar backgrounds (such as vegetation patterns) when relying solely on local features. We propose DRRNet, a four-stage architecture characterized by a "context-detail-fusion-refinement" pipeline to address these issues. Specifically, we introduce an Omni-Context Feature Extraction Module to capture global camouflage patterns and a Local Detail Extraction Module to supplement microstructural information for the full-scene context module. We then design a module for forming dual representations of scene understanding and structural awareness, which fuses panoramic features and local features across various scales. In the decoder, we also introduce a reverse refinement module that leverages spatial edge priors and frequency-domain noise suppression to perform a two-stage inverse refinement of the output. By applying two successive rounds of inverse refinement, the model effectively suppresses background interference and enhances the continuity of object boundaries. Experimental results demonstrate that DRRNet significantly outperforms state-of-the-art methods on benchmark datasets. Our code is available at https://github.com/jerrySunning/DRRNet.