Language-Guided Structure-Aware Network for Camouflaged Object Detection

TL;DR

This paper introduces a novel language-guided, structure-aware neural network for camouflaged object detection, integrating textual priors, frequency domain edge enhancement, and boundary refinement to improve detection accuracy.

Contribution

The proposed LGSAN combines CLIP-guided text and image masks with multi-scale features, Fourier-based edge enhancement, and structure-aware attention for improved camouflaged object detection.

Findings

Achieves state-of-the-art performance on multiple COD datasets.

Effectively integrates textual semantic priors for focused detection.

Demonstrates robustness and high accuracy in complex scenes.

Abstract

Camouflaged Object Detection (COD) aims to segment objects that are highly integrated with the background in terms of color, texture, and structure, making it a highly challenging task in computer vision. Although existing methods introduce multi-scale fusion and attention mechanisms to alleviate the above issues, they generally lack the guidance of textual semantic priors, which limits the model's ability to focus on camouflaged regions in complex scenes. To address this issue, this paper proposes a Language-Guided Structure-Aware Network (LGSAN). Specifically, based on the visual backbone PVT-v2, we introduce CLIP to generate masks from text prompts and RGB images, thereby guiding the multi-scale features extracted by PVT-v2 to focus on potential target regions. On this foundation, we further design a Fourier Edge Enhancement Module (FEEM), which integrates multi-scale features with high-frequency information in the frequency domain to extract edge enhancement features. Furthermore, we propose a Structure-Aware Attention Module (SAAM) to effectively enhance the model's perception of object structures and boundaries. Finally, we introduce a Coarse-Guided Local Refinement Module (CGLRM) to enhance fine-grained reconstruction and boundary integrity of camouflaged object regions. Extensive experiments demonstrate that our method consistently achieves highly competitive performance across multiple COD datasets, validating its effectiveness and robustness.