FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-aware and Contrastive Learning

2026-03-24

AI Summary

Weakly supervised camouflaged object detection (COD) often suffers from non-camouflaged responses, localized activations, extreme predictions, and ambiguous boundaries, leading to significantly inferior performance compared to fully supervised approaches. To address these challenges, this work proposes the FCL-COD framework, which introduces frequency-domain awareness into the Segment Anything Model (SAM) for the first time. By integrating frequency-aware low-rank adaptation (FoRA), gradient-aware contrastive learning, and multi-scale frequency representations, the method effectively mitigates various response biases under weak supervision and enhances boundary delineation. Extensive experiments demonstrate that FCL-COD outperforms existing weakly supervised methods on three mainstream COD benchmarks and even surpasses several fully supervised models, substantially advancing detection accuracy in weakly supervised settings.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Unsupervised & Self-Supervised Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Existing camouflage object detection (COD) methods typically rely on fully-supervised learning guided by mask annotations. However, obtaining mask annotations is time-consuming and labor-intensive. Compared to fully-supervised methods, existing weakly-supervised COD methods exhibit significantly poorer performance. Even for the Segment Anything Model (SAM), there are still challenges in handling weakly-supervised camouflage object detection (WSCOD), such as: a. non-camouflage target responses, b. local responses, c. extreme responses, and d. lack of refined boundary awareness, which leads to unsatisfactory results in camouflage scenes. To alleviate these issues, we propose a frequency-aware and contrastive learning-based WSCOD framework in this paper, named FCL-COD. To mitigate the problem of non-camouflaged object responses, we propose the Frequency-aware Low-rank Adaptation (FoRA) method, which incorporates frequency-aware camouflage scene knowledge into SAM. To overcome the challenges of local and extreme responses, we introduce a gradient-aware contrastive learning approach that effectively delineates precise foreground-background boundaries. Additionally, to address the lack of refined boundary perception, we present a multi-scale frequency-aware representation learning strategy that facilitates the modeling of more refined boundaries. We validate the effectiveness of our approach through extensive empirical experiments on three widely recognized COD benchmarks. The results confirm that our method surpasses both state-of-the-art weakly supervised and even fully supervised techniques.

Problem

• Camouflaged Object Detection
• Weakly Supervised Learning
• Boundary Awareness
• Non-camouflage Responses
• Local Responses

Innovation

• Frequency-aware Learning
• Contrastive Learning
• Weakly Supervised Camouflaged Object Detection
• Low-rank Adaptation
• Boundary Refinement