Weakly-Supervised Camouflaged Object Detection via SAM-Guided Resolution Iteration Learning
- 23 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 12 (2) , 403-415
Abstract
Weakly supervised camouflaged object detection (WS-COD) aims to address the critical task of identifying visually assimilated objects concealed within heterogeneous backgrounds under sparse supervisory signals. However, current WS-COD frameworks suffer from compromised structural integrity, stemming from cross-hierarchical feature discrepancy and constrained cross-level information flow, which induces structural misalignment and context fragmentation in multi-granularity feature fusion. To overcome the limitation, we propose a novel SAM-guided Resolution Iteration Learning Network (SAM-RNet) that synergizes foundation model priors with multi-resolution feature refinement. Our technical contributions are threefold: (1) We utilize the Segment Anything Model (SAM) to produce high-quality masks, effectively mitigating supervision insufficiency through large-scale visual knowledge distillation. (2) We design a resolution iteration mechanism where high-resolution features progressively refine low-resolution counterparts through an Interactive Refinement Module (IRM) - a dual-branch architecture enabling hierarchical feature interaction and enhancement through branch collaboration and attention mechanism, complemented by an iterative feedback loss to enforce multi-scale feature learning. (3) We develop a Decoder with cross-layer fusion operations, enabling the aggregation of features from object and background contexts for precise object segmentation. Finally, extensive experiments demonstrate that SAM-RNet is superior to existing WS-COD methods across three COD datasets, achieving average improvements of 4.37%, 4.60%, 7.00%, and 24.06% in $S_{\alpha }$ , $E_{\phi }$ , $F_{\beta }^{\omega }$ , and $M$ , respectively.
Keywords
Funding Information
- National Natural Science Foundation of China (62471124)
- Natural Science Foundation of Heilongjiang Province (LH2022F005)
- Young Top Talents Fund in the School of Electrical Information Engineering of Northeast Petroleum University (DYDQQB202204)
This publication has 74 references indexed in Scilit:
- Research on collaborative camouflaged object detection under dual domain entanglementImage and Vision Computing, 2025
- Lightweight hybrid attention RGB-D networks for accurate camouflaged object detectionThe Visual Computer, 2025
- Camouflaged Object Detection via location-awareness and feature fusionImage and Vision Computing, 2024
- Camouflage detection: Optimization-based computer vision for Alligator sinensis with low detectability in complex wild environmentsEcological Informatics, 2024
- Advances in deep concealed scene understandingVisual Intelligence, 2023
- Ternary symmetric fusion network for camouflaged object detectionApplied Intelligence, 2023
- Trichomonas Vaginalis Segmentation in Microscope Images2022
- Anabranch network for camouflaged object segmentationComputer Vision and Image Understanding, 2019
- Segmentation-based deep-learning approach for surface-defect detectionJournal of Intelligent Manufacturing, 2019
- A Tutorial on the Cross-Entropy MethodAnnals of Operations Research, 2005