Consensus-Aware Multi-Source Fusion for Reference-Guided Camouflaged Object Detection

Junyang Xia; Luocheng Zhang; Wenwen Pan; Chifeng Zhu; Yang Yang; Xinchun Liu; Jiajun Ding

cs.CVSep 30, 2026

Consensus-Aware Multi-Source Fusion for Reference-Guided Camouflaged Object Detection

Authors: Junyang Xia, Luocheng Zhang, Wenwen Pan, Chifeng Zhu, Yang Yang, Xinchun Liu, Jiajun Ding

Organizations: School of Computer Science, Hangzhou Dianzi University, Hangzhou 310018, China

Abstract

Reference-guided camouflaged object detection aims to segment a target whose visual appearance closely resembles its surroundings by exploiting auxiliary reference samples. The task remains difficult because reference samples contain inconsistent target cues, while generic visual representations are not inherently aligned with the target specified by the references. To handle these problems, we present a consensus-aware multi-source fusion framework. Reference-Conditioned Dual-Backbone Fusion (RCDF) couples trainable PVTv2 query features with frozen DINOv3 representations and uses reference-conditioned correlation to select foundation-model evidence before multi-scale fusion. The framework also aggregates multiple references through cross-reference consensus aggregation and injects reference information at semantic depths matched to the query features. Extensive experiments demonstrate the effectiveness of the proposed method. The results further show that reference consensus, target-conditioned foundation features, and hierarchical decoding provide complementary improvements under the evaluation protocol. The source code will be made publicly available upon acceptance.

Figures & tables

Figure 1: Representative results for reference-guided camouflaged object detection. Columns show the input, ground truth (GT), predictions from UAT, R2CNet, Qwen+SAM, and our method. The displayed $S_{m}$ values accompany examples with low contrast, thin structures, and multiple targets.

Figure 2: Overview of the consensus-aware multi-source fusion framework. CRCA aggregates heterogeneous references into consensus priors. RCDF couples the trainable PVTv2 and frozen DINOv3 backbones by using reference-conditioned correlation to gate foundation features before multi-scale fusion. The HRFD stage performs spatial cross-attention at deep stages, vector-based modulation at shallow stages, and HMU decoding to produce the final mask and auxiliary predictions.

Figure 3: Internal structure of cross-reference consensus aggregation. The Reference Reliability Estimator (RRE) applies self-attention across the reference dimension and predicts reliability scores after normalization and projection. Reference-Guided Fusion (RGF) then uses the normalized weights $\{\alpha_{k}\}_{k=1}^{K}$ to aggregate the reference features $\{R_{k}\}_{k=1}^{K}$ into the consensus representation $\bar{R}$ .

Method	Backbone	Overall				Single-object				Multi-object
		$S_{m}\uparrow$	$\alpha E\uparrow$	$wF\uparrow$	MAE $\downarrow$	$S_{m}\uparrow$	$\alpha E\uparrow$	$wF\uparrow$	MAE $\downarrow$	$S_{m}\uparrow$	$\alpha E\uparrow$	$wF\uparrow$	MAE $\downarrow$
R2CNet	ResNet-50	0.805	0.879	0.669	0.036	0.810	0.880	0.674	0.035	0.747	0.872	0.602	0.046
UAT	PVTv2-B2	0.855	0.912	0.757	0.026	0.859	0.913	0.761	0.025	0.805	0.900	0.701	0.033
Qwen+SAM	–	0.852	0.917	0.793	0.029	0.861	0.926	0.805	0.027	0.778	0.844	0.683	0.047
RefOnce	PVTv2-B2	0.890	0.937	0.819	0.019	0.894	0.937	0.825	0.018	0.853	0.930	0.767	0.024
Ours / All components	PVTv2-B2	0.895	0.941	0.825	0.017	0.899	0.943	0.830	0.016	0.859	0.930	0.780	0.021

Table 1: Quantitative comparison on the overall, single-object, and multi-object subsets. Higher values are better for

S_{m}

\alpha E

, and

wF

; lower values are better for MAE.

Figure 4: Qualitative comparison on representative query–reference pairs. From top to bottom, the rows show the query image, reference image, ground truth, and predictions from R2CNet, UAT, Qwen+SAM, and our method.

CRCA	RCDF	HRFD	Overall				Single-object				Multi-object
			$S_{m}\uparrow$	$\alpha E\uparrow$	$wF\uparrow$	MAE $\downarrow$	$S_{m}\uparrow$	$\alpha E\uparrow$	$wF\uparrow$	MAE $\downarrow$	$S_{m}\uparrow$	$\alpha E\uparrow$	$wF\uparrow$	MAE $\downarrow$
$-$	$-$	$-$	0.8550	0.9120	0.7570	0.0260	0.8590	0.9130	0.7610	0.0250	0.8050	0.9000	0.7010	0.0330
$\checkmark$	$-$	$-$	0.8610	0.9160	0.7660	0.0247	0.8654	0.9172	0.7722	0.0239	0.8210	0.9050	0.7100	0.0315
$-$	$\checkmark$	$-$	0.8720	0.9230	0.7850	0.0229	0.8762	0.9242	0.7905	0.0222	0.8340	0.9120	0.7350	0.0288
$-$	$-$	$\checkmark$	0.8660	0.9190	0.7740	0.0238	0.8703	0.9202	0.7800	0.0231	0.8270	0.9080	0.7200	0.0300
$\checkmark$	$\checkmark$	$-$	0.8810	0.9320	0.8060	0.0208	0.8847	0.9331	0.8111	0.0202	0.8480	0.9220	0.7600	0.0258

Table 2: Full-factorial ablation of CRCA, RCDF, and HRFD on the Overall, Single-object, and Multi-object subsets. Higher values are better for

S_{m}

\alpha E

, and

wF

; lower values are better for MAE.

Figure 5: Qualitative visualization of progressive component variants. The labels embedded in the figure denote the progressive variants and are distinct from the factorial combinations evaluated in Table 2 .

Study	Setting	$S_{m}\uparrow$	$\alpha E\uparrow$	$wF\uparrow$	MAE $\downarrow$
Edge-loss weight	0.05	0.8884	0.9402	0.8162	0.0174
	0.10	0.8904	0.9334	0.8108	0.0177
	0.50	0.8885	0.9318	0.8192	0.0170
	0.20 (selected)	0.8946	0.9414	0.8253	0.0168
Correlation-scale initialization	1	0.8874	0.9368	0.8172	0.0172
	3	0.8873	0.9394	0.8170	0.0172

Table 3: Three representative one-factor parameter studies. Each block changes only the named setting, while selected rows repeat the shared complete-model result. Higher values are better for

S_{m}

\alpha E

, and

wF

; lower values are better for MAE.

Figure 6: Qualitative comparison of correlation-scale initialization. Columns show the input, ground truth, scales of 1, 3, and 5, and the selected scale of 20 (Ours). Red boxes enlarge challenging regions and boundaries.

Figure 7: Qualitative comparison of ASPP dilation settings. Columns show the input, ground truth, groups $(1,3,5)$ and $(2,4,6)$ , and the selected group $(3,6,9)$ (Ours). Red boxes enlarge challenging regions and boundaries.

Item	Measurement
Training iteration time (batch size 8)	140.68 ms/step
Inference latency (FP32, 5-shot)	24.31 ms/image
Inference throughput	41.13 FPS
Computational cost	143.54 GFLOPs / 71.77 GMACs
Peak inference memory	548.6 MiB
Peak training memory	7008.8 MiB

Table 4: Computational efficiency on one NVIDIA GeForce RTX 4090 D. Inference uses FP32, a

384\times 384

query, five references, and cached ICON-R features; latency excludes reference-feature extraction.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Figure A1: Qualitative visualization of reference-conditioned DINOv3 feature selection. From left to right, the columns show the input, ground truth (GT), baseline prediction, output with the DINOv3 prior, output after the Semantic Gate, and gate map. In the present formulation, the Semantic Gate denotes RCDF’s reference-conditioned correlation map.

Figure A2: Qualitative visualization of progressive reference-guided refinement. From left to right, the columns show the input, GT, outputs after the Semantic Gate, Cross-Attention, and Ref. Interaction, followed by residual error. The latter two stages are the reference-guided interactions in HRFD.

Explore similar work

EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detection
Mar 12, 2026Shuo Jiang, Gaojia Zhang, Min Tan +2Camouflaged Object Detection Pseudo-Label Quality
Zhejiang Key Laboratory of Space Information Sensing and Transmission, Hangzhou Dianzi University · Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University · College of Computer Science and Technology, Zhejiang University
Phantom-Insight: Adaptive Multi-cue Fusion for Video Camouflaged Object Detection with Multimodal LLM
Sep 8, 2025Hua Zhang, Changjiang LuoCamouflaged Object Detection Video Object Segmentation
Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences
MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection
Nov 16, 2025Leena Alghamdi, Muhammad Usman, Hafeez Anwar +2Camouflaged Object Detection Object Detection
King Fahd University of Petroleum and Minerals, KSA · Ontario Tech University, Canada · National University of Computer and Emerging Sciences, Pakistan +2

Mar 12, 2026, cs.CVJ/K move · Enter open · S save

EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detection

Shuo Jiang, Gaojia Zhang, Min Tan, Yufei Yin+1

Zhejiang Key Laboratory of Space Information Sensing and Transmission, Hangzhou Dianzi University · Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University · College of Computer Science and Technology, Zhejiang University

Camouflaged Object Detection Pseudo-Label Quality High Confidence Pseudo-Labels Texture Refinement

Open paper AskPDF arXiv

Unsupervised Camouflaged Object Detection (UCOD) remains a challenging task due to the high intrinsic similarity between target objects and their surroundings, as well as the reliance on noisy pseudo-labels that hinder fine-grained texture learning. While existing refinement strategies aim to alleviate label noise, they often overlook intrinsic perceptual cues, leading to boundary overflow and structural ambiguity. In contrast, learning without pseudo-label guidance yields coarse features with significant detail loss. To address these issues, we propose a unified UCOD framework that enhances both the reliability of pseudo-labels and the fidelity of features. Our approach introduces the Multi-Cue Native Perception module, which extracts intrinsic visual priors by integrating low-level texture cues with mid-level semantics, enabling precise alignment between masks and native object information. Additionally, Pseudo-Label Evolution Fusion intelligently refines labels through teacher-student interaction and utilizes depthwise separable convolution for efficient semantic denoising. It also incorporates Spectral Tensor Attention Fusion to effectively balance semantic and structural information through compact spectral aggregation across multi-layer attention maps. Finally, Local Pseudo-Label Refinement plays a pivotal role in local detail optimization by leveraging attention diversity to restore fine textures and enhance boundary fidelity. Extensive experiments on multiple UCOD datasets demonstrate that our method achieves state-of-the-art performance, characterized by superior detail perception, robust boundary alignment, and strong generalization under complex camouflage scenarios. Code is available at https://github.com/JSLiam94/EReCu.

Abstract

Explore similar work

EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detection

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

MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection