Language-Guided Structure-Aware Network for Camouflaged Object Detection

Min Zhang

cs.CVMar 25, 2026

Language-Guided Structure-Aware Network for Camouflaged Object Detection

Authors: Min Zhang

Organizations: School of Artificial Intelligence, Chongqing University of Technology, Chongqing, 401120, China

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.

Figures & tables

Figure 1: The architecture of LGSAN. The overall framework of the model consists of five key components: the PVT-v2 backbone, the CLIP backbone, the FEEM, the SAAM, and the CGRLM. Refer to Section 3 for details.

Figure 2: The architecture of the FEEM. The FEEM generates edge enhancement features through multi-scale fusion, edge enhancement, and high-frequency modeling in the frequency domain.

Figure 3: The SAAM introduces semantic information of camouflaged objects into a lightweight attention framework to highlight camouflaged regions, while incorporating edge enhancement features to emphasize boundary information, thereby enabling the model to focus on structural and boundary details of camouflaged objects at high resolution.

Figure 4: The CGLRM employs channel and spatial attention to obtain global guidance, performs local refinement through 2×2 spatial partitioning, thereby ensuring structural consistency and boundary integrity.

Figure 5: The heatmaps of LGSAN from $O_{4}$ to $O_{1}$ illustrate the progressive refinement process, while the heatmaps of $M_{1}$ and $O_{e}$ are also presented for comparison.

Method	Pub./Year	CAMO				COD10K				NC4k
Method	Pub./Year	$S_{\alpha}\uparrow$	$E_{\phi}\uparrow$	$F^{w}_{\beta}\uparrow$	$M\downarrow$	$S_{\alpha}\uparrow$	$E_{\phi}\uparrow$	$F^{w}_{\beta}\uparrow$	$M\downarrow$	$S_{\alpha}\uparrow$	$E_{\phi}\uparrow$	$F^{w}_{\beta}\uparrow$	$M\downarrow$
BGNet	IJCAI’22	0.812	0.870	0.749	0.073	0.831	0.901	0.722	0.033	0.851	0.907	0.788	0.044
ZoomNet	CVPR’22	0.820	0.892	0.752	0.066	0.838	0.911	0.729	0.029	0.853	0.912	0.784	0.059
EVP	CVPR’23	0.846	0.895	0.777	0.059	0.843	0.907	0.742	0.029
EAMNet	ICME’23	0.831	0.890	0.763	0.064	0.839	0.907	0.733	0.029	0.862	0.916	0.801	0.040
FSPNet	CVPR’23	0.856	0.899	0.799	0.050	0.851	0.895	0.735	0.026	0.879	0.915	0.816	0.035

Table 1: Quantitative comparison with state-of-the-art methods for COD on 3 benchmarks using 4 widely used evaluation metrics (

S_{\alpha},E_{\phi},F^{w}_{\beta},M

). “↑” / “↓” indicates that larger/smaller is better. The best results are in bold ,**** means the model was not tested on this dataset.

Figure 6: Compared with existing methods, the proposed approach achieves superior performance in terms of localization accuracy, structural integrity, and boundary details across multiple categories of camouflaged objects.

Model	Method	COD10K
Model	Method	$S_{\alpha}\uparrow$	$E_{\phi}\uparrow$	$F^{w}_{\beta}\uparrow$	$M\downarrow$
a	B	0.831	0.905	0.706	0.032
b	B + C	0.890	0.947	0.825	0.019
c	B + C + E	0.893	0.948	0.830	0.018
d	B + C + E + SC	0.894	0.950	0.833	0.018

Table 2: Ablation study of LGSAN. In the table, “B” denotes the baseline composed of PVT-v2-B3 and a simple CNN, “E” represents the FEEM module, “c” indicates the use of CLIP for generating the

M_{1}

mask, and “SC” refers to the SAAM and CGLRM.

Explore similar work

Aug 8, 2026

LAD-COD: Language-Aligned Dense Perception for Camouflaged Object Detection

Camouflaged object detection (COD) aims to segment objects that exhibit high visual similarity to their surroundings, which reduces foreground-background discriminability and weakens boundary evidence across appearance, texture, and structure. Such limitations motivate the use of instruction-conditioned semantics as top-down guidance for identifying which weak visual cues are relevant to the target. Recent segmentation systems built on large multimodal models (LMMs) demonstrate this possibility through instruction-conditioned target embeddings that guide mask decoding. However, in this language-to-mask paradigm, the generated target embedding conditions mainly the mask decoder, leaving the dense visual features that must preserve low-contrast boundaries and fine local structure without explicit guidance. We propose Language-Aligned Dense perception for COD (LAD-COD), a framework that aligns top-down semantic target guidance with bottom-up hierarchical visual features. Instead of fully adapting a large generic image encoder, LAD-COD learns a trainable hierarchical visual branch that captures camouflage-sensitive texture, boundary, and contextual information. To align these features with the target embedding, LAD-COD applies Language-Aligned Dual Visual Fusion (LADVF), which extends the embedding beyond sparse prompting to query patch-level language-aligned features and to gate their residual integration with the hierarchical features. This design allows semantic information to guide localization while preserving the fine structural details needed for camouflage segmentation. Experiments on CAMO, COD10K, and NC4K show that LAD-COD obtains the best reported value in all 12 dataset-metric comparisons.

Shangye Song, Tianzhi Zhu, Syed Ariff Syed Hesham +2

School of Computer Science, The University of Auckland · VCIP, College of Computer Science, Nankai University · School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore +4

Text-Guided Image Segmentation Vision-Language Alignment Multimodal Fusion Camouflaged Object Detection

Ask PDF

Jul 2, 2026

CamoNAS: Neural Architecture Search for Enhanced Camouflaged Object Detection

Camouflaged Object Detection (COD) aims to locate and segment objects that blend into their surroundings, presenting challenges due to weak edge cues and ill-defined boundaries. Traditional COD models rely on hand-designed architectures and multi-scale feature fusion, which are often guided by intuition rather than systematic search. This paper introduces CamoNAS, a frequency-aware multi-resolution Neural Architecture Search (NAS) framework for COD. CamoNAS automatically searches both cell-level operations and network-level downsampling paths, forming a hierarchical search space tailored to detect camouflaged objects. Additionally, it adopts an RGB frequency dual-stream architecture, where a learnable wavelet transform complements the RGB spatial stream. CamoNAS achieves state-of-the-art performance on four COD benchmarks (CAMO, COD10K, NC4K, CHAMELEON), highlighting the effectiveness of NAS for COD. Our code is available at https://github.com/rendaweiSIMIT/CamoNAS.

Dawei Ren, Yan Zhang, Hongying Tang +2

Science and Technology on Micro-system Laboratory, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, 865 Changning Road, Shanghai, 200050, China. · University of Chinese Academy of Sciences, No. 19(A) Yuquan Road, Shijingshan District, Beijing, 100049, Beijing, China. · School of Information Science and Technology, Shanghaitech University, Shanghai, China.

Neural Architecture Search Camouflaged Object Detection

Ask PDF

Sep 8, 2025

Phantom-Insight: Adaptive Multi-cue Fusion for Video Camouflaged Object Detection with Multimodal LLM

Video camouflaged object detection (VCOD) is challenging due to dynamic environments. Existing methods face two main issues: (1) SAM-based methods struggle to separate camouflaged object edges due to model freezing, and (2) MLLM-based methods suffer from poor object separability as large language models merge foreground and background. To address these issues, we propose a novel VCOD method based on SAM and MLLM, called Phantom-Insight. To enhance the separability of object edge details, we represent video sequences with temporal and spatial clues and perform feature fusion via LLM to increase information density. Next, multiple cues are generated through the dynamic foreground visual token scoring module and the prompt network to adaptively guide and fine-tune the SAM model, enabling it to adapt to subtle textures. To enhance the separability of objects and background, we propose a decoupled foreground-background learning strategy. By generating foreground and background cues separately and performing decoupled training, the visual token can effectively integrate foreground and background information independently, enabling SAM to more accurately segment camouflaged objects in the video. Experiments on the MoCA-Mask dataset show that Phantom-Insight achieves state-of-the-art performance across various metrics. Additionally, its ability to detect unseen camouflaged objects on the CAD2016 dataset highlights its strong generalization ability.

Hua Zhang, Changjiang Luo

Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences

Video Object Segmentation Vision Foundation Model Adaptation Camouflaged Object Detection

Ask PDF