DRRNet: Macro-Micro Feature Fusion and Dual Reverse Refinement for Camouflaged Object Detection
Preprint
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.Keywords
All Related Versions
This publication has 62 references indexed in Scilit:
- Frequency-Spatial Entanglement Learning for Camouflaged Object Detection2024
- Locate, enhance and fuse: a progressively optimized network for camouflaged object detectionMultimedia Tools and Applications, 2024
- Camouflaged Object Segmentation with Omni PerceptionInternational Journal of Computer Vision, 2023
- OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers2022
- Synthetic data augmentation for surface defect detection and classification using deep learningJournal of Intelligent Manufacturing, 2020
- Kvasir-SEG: A Segmented Polyp Dataset2019
- CBAM: Convolutional Block Attention Module2018
- Partially Camouflaged Object Tracking using Modified Probabilistic Neural Network and Fuzzy Energy based Active ContourInternational Journal of Computer Vision, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancerInternational Journal of Computer Assisted Radiology and Surgery, 2013