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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Xia, J., Zhang, L., Pan, W., Zhu, C., Yang, Y., Liu, X., & Ding, J. (2026). Consensus-Aware Multi-Source Fusion for Reference-Guided Camouflaged Object Detection. https://omanscience.com/en/articles/consensus-aware-multi-source-fusion-for-reference-guided-camouflaged-object-detection
MLA 9
Xia, Junyang, et al. "Consensus-Aware Multi-Source Fusion for Reference-Guided Camouflaged Object Detection." https://omanscience.com/en/articles/consensus-aware-multi-source-fusion-for-reference-guided-camouflaged-object-detection.
Chicago (author–date)
Xia, Junyang, Luocheng Zhang, Wenwen Pan, Chifeng Zhu, Yang Yang, Xinchun Liu, and Jiajun Ding. 2026. "Consensus-Aware Multi-Source Fusion for Reference-Guided Camouflaged Object Detection." https://omanscience.com/en/articles/consensus-aware-multi-source-fusion-for-reference-guided-camouflaged-object-detection.
Harvard
Xia, J., Zhang, L., Pan, W., Zhu, C., Yang, Y., Liu, X. and Ding, J. (2026) 'Consensus-Aware Multi-Source Fusion for Reference-Guided Camouflaged Object Detection', Available at: https://omanscience.com/en/articles/consensus-aware-multi-source-fusion-for-reference-guided-camouflaged-object-detection.
Vancouver
Xia J, Zhang L, Pan W, Zhu C, Yang Y, Liu X, et al. Consensus-Aware Multi-Source Fusion for Reference-Guided Camouflaged Object Detection. https://omanscience.com/en/articles/consensus-aware-multi-source-fusion-for-reference-guided-camouflaged-object-detection
IEEE
J. Xia, L. Zhang, W. Pan, C. Zhu, Y. Yang, X. Liu, and J. Ding, "Consensus-Aware Multi-Source Fusion for Reference-Guided Camouflaged Object Detection," https://omanscience.com/en/articles/consensus-aware-multi-source-fusion-for-reference-guided-camouflaged-object-detection.