Traditional contrastive learning algorithms have relied on instance discrimination, which is easy to introduce false negative samples, resulting in algorithm converges to suboptimal solutions and degenerating the performance of downstream tasks. To address this issue, this paper proposes a multi-branch contrastive learning algorithm based on relationship consistency. This algorithm incorporates a nearest neighbor set into the branch network, providing positive samples with their semantic consistency and avoiding false negative samples. Combined with multi-branch training using data augmentation, it minimizes KL divergence to pull positive samples with semantic consistency together and push away negative samples, which enhances the representation ability of network. The temperature parameters in different branches control the smoothness of the sharpen distribution, ensuring the reliability of feature representations. Finally, the method is evaluated on five public datasets and compared with state-of-the-art contrastive learning methods, all achieving satisfactory results.
[1] NOROOZI M, FAVARO P. Unsupervised learning of visual representations by solving jigsaw puzzles[C] //European Conference on Computer Vision. Cham: Springer, 2016: 69-84.DOI: 10.1007/978-3-319-46466-4_5.
[2] DOERSCH C, GUPTA A, EFROS A A. Unsupervised visual representation learning by context prediction[C] //2015 IEEE International Conference on Computer Vision(ICCV), Santiago, Chile, IEEE, 2015: 1422-1430. DOI: 10.1109/ ICCV.2015.167.
[3] CHEN J, SUN L,XIE B. LSPC: Exploring contrastive clustering based on local semantic information and prototype[J]. Inf Syst, 2024, 121:102336. DOI:10.1016/j.is.2023.102336.
[4] WANG W, CHEN J, ZHANG X, et al. Combining core points and cluster-ievel semantic similarity for self-supervised clustering[J]. Int J Mach Learn and Cybern,2024,15(8):3127-3142.DOI:10.1007/s13042-023-02084-1.
[5] 赵宇,舒巧媛.基于渐进式混合对比学习的无监督领域自适应行人再识别[J].电子学报,2025,53(6):1829-1846.
[6] 张北辰,李亮,查正军,等.基于跨模态对比学习的视觉问答主动学习方法[J].计算机学报, 2022,45: 1730-1745.
[7] 吴冠荣,李元祥,王艺霖,等.基于对比学习的小样本金属表面损伤分类[J].计算机工程, 2024, 50(3):1-12. DOI: 10. 19678/j.issn.1000-3428.0067599.
[8] HU J, HU M, WU Y, et al. A lightweight single-view contrastive learning hypergraph neural network for food-microbe-disease association prediction[J]. BMC Bioinformatics, 2025, 26(1):273. DOI:10.1186/s12859-025-06283-1.
[9] 吴晗飞,俸彬,李梦华,等.InSAR时序形变数据的自监督对比学习聚类方法[J].遥感学报,2025,29(7):2442-2456. DOI:10.11834/jrs.20254393.
[10] YU S, WANG H, HUA M, et al. Sparse graph cascade multi-kernel fusion contrastive learning for microbe-disease association prediction[J]. Expert Syst Appl, 2024, 252(PartA):124092. DOI:10.1016/j.eswa.2024.124092.
[11] WANG Y, ZHANG J, WANG Y. Do generated data always help contrastive learning?[C] //International Conference on Learning Representations(ICLR 2024), Vienna, Austria, 2024,1-19.
[12] WANG Y, ZHANG Q, GUO Y, et al.Non-negative contrastive learning[C] //International Conference on Learning Representations(ICLR 2024), Vienna, Austria, 2024,1-22.
[13] CUI J, WEN H, WANG Y. An augmentation-aware theory for self-supervised contrastive learning[C] //Proceedings of the 42nd International Conference on Machine Learning(ICML), 2025.
[14] CHEN T, KORNBLITH S, NOROUZI M, et al. A simple framework for contrastive learning of visual representations [C] // the 37th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020: 1597-1607.
[15] HE K M, FAN H Q, WU Y X, et al. Momentum contrast for unsupervised visual representation learning[C] //2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Seattle, WA, USA. IEEE, 2020: 9726- 9735. DOI: 10.1109/CVPR42600.2020.00975.
[16] CHEN X L, FAN H Q, GIRSHICK R, et al. Improved baselines with momentum contrastive learning[EB/OL]. 2020: arXiv: 2003.04297. http://arxiv.org/abs/2003.04297.
[17] GRILL J B, STRUB F, ALTCHÉ F, et al. Bootstrap your own latent: a new approach to self-supervised Learning[C] //Advances in neural information processing systems, 2020, 33: 21271-21284.
[18] CHEN X L, HE K M. Exploring simple Siamese representation learning[C] //2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Nashville, TN, USA. IEEE, 2021: 15745-15753. DOI: 10.1109/ CVPR46437.2021.01549.
[19] WU Z R, XIONG Y J, YU S X, et al. Unsupervised feature learning via non-parametric instance discrimination[C] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA. IEEE, 2018: 3733-3742. DOI: 10.1109/CVPR.2018.00393.
[20] ZHENG M K, YOU S, WANG F, et al. ReSSL: Relational self-supervised learning with weak augmentation[C] // Advances in Neural Information Processing Systems, 2021, 34: 2543-2555.
[21] DWIBEDI D, AYTAR Y, TOMPSON J, et al. With a little help from my friends: nearest-neighbor contrastive learning of visual representations[C] //2021 IEEE/CVF International Conference on Computer Vision(ICCV), Montreal, QC, Canada, IEEE, 2021: 9568-9577. DOI: 10.1109/ICCV48922.2021.00945.
[22] VAN DEN OORD A, LI Y Z, VINYALS O. Representation learning with contrastive predictive coding[EB/OL]. 2018: arXiv: 1807.03748. http://arxiv.org/abs/1807.03748.
[23] COATES A, NG A, LEE H. An analysis of single-layer networks in unsupervised feature learning[C] // Artificial Intelligence and Statistics Conference, 2011: 215-223.
[24] DENG J, DONG W, SOCHER R, et al. ImageNet: A large-scale hierarchical image database[C] //2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA. IEEE, 2009: 248-255. DOI: 10.1109/CVPR. 2009.5206848.
[25] ZBONTAR J, JING L, MISRA I, et al. Barlow twins: Self-supervised learning via redundancy reduction [C] //International conference on machine learning, ICML, 2021: 12310-12320.
[26] YEH C H, HONG C Y, HSU Y C, et al. Decoupled contrastive learning[C] // 17th European Conference on Computer Vision, Tel Aviv, Israel, 2022: 668-684. DOI: 10.1007/978-3-031-19809-0_38.
[27] FENG C, PATRAS I. Adaptive soft contrastive learning[C] //2022 26th International Conference on Pattern Recognition(ICPR), Montreal, QC, Canada, IEEE, 2022: 2721-2727. DOI: 10.1109/ICPR56361.2022.9956660. (
