Unsupervised Deep Hashing Image Retrieval Based on Bias Suppressing Contrastive Learning
Author:
  • Article
  • | |
  • Metrics
  • |
  • Reference [35]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    In the contemporary field of unsupervised deep hashing research, methods predicated on contrastive learning are predominant. However, sampling bias brought about by the random extraction of negative samples in contrastive learning deteriorates image retrieval accuracy. To address the issue, this study proposes a novel unsupervised deep hashing based on bias suppressing contrastive learning (BSCDH). It proposes a bias suppression method (BSS) based on a contrastive learning framework. This method approximates incorrect negative samples as extremely hard negative samples and designs a bias suppression coefficient to suppress these extremely hard negative samples, thereby alleviating the negative impact of sampling bias. The corresponding suppression coefficient value is determined based on the similarity between the current negative sample and the query sample. Distance relationship between the current negative sample and adjacent hash centers is introduced to correct the suppression coefficient value, reducing the possibility of excessive suppression of normal negative samples. Ultimately, the mAP@5000 of the BSCDH method (64 bits) achieves 0.696, 0.833, and 0.819 respectively on the CIFAR-10, FLICKR25K, and NUS-WIDE datasets, demonstrating a significant performance advantage over the baseline. Extensive experiments conducted in this paper verify that BSCDH exhibits high retrieval accuracy in unsupervised image retrieval methods and can effectively address sampling bias.

    Reference
    [1] Luo X, Wang HX, Wu DQ, et al. A survey on deep hashing methods. ACM Transactions on Knowledge Discovery from Data, 2023, 17(1): 15.
    [2] Weiss Y, Torralba A, Fergus R. Spectral hashing. Proceedings of the 21st International Conference on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2008. 1753–1760.
    [3] Gong YC, Lazebnik S, Gordo A, et al. Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(12): 2916–2929.
    [4] Kaya M, Bilge HŞ. Deep metric learning: A survey. Symmetry, 2019, 11(9): 1066.
    [5] Chen T, Kornblith S, Norouzi M, et al. A simple framework for contrastive learning of visual representations. Proceedings of the 37th International Conference on Machine Learning. PMLR, 2020. 149.
    [6] Albelwi S. Survey on self-supervised learning: Auxiliary pretext tasks and contrastive learning methods in imaging. Entropy, 2022, 24(4): 551.
    [7] Jaiswal A, Babu AR, Zadeh MZ, et al. A survey on contrastive self-supervised learning. Technologies, 2020, 9(1): 2.
    [8] Qiu ZX, Su QL, Ou ZJ, et al. Unsupervised hashing with contrastive information bottleneck. Proceedings of the 30th International Joint Conference on Artificial Intelligence. Montreal: ijcai.org, 2021. 959–965.
    [9] Luo X, Ma ZY, Cheng W, et al. Improve deep unsupervised hashing via structural and intrinsic similarity learning. IEEE Signal Processing Letters, 2022, 29: 602–606.
    [10] Mikriukov G, Ravanbakhsh M, Demir B. Unsupervised contrastive hashing for cross-modal retrieval in remote sensing. Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing. Singapore: IEEE, 2022. 4463–4467.
    [11] Lee W, Byun SY, Park M. Unsupervised soft-to-hard hashing with contrastive learning. Computer Vision and Image Understanding, 2023, 233: 103713.
    [12] Wei RK, Liu Y, Song JK, et al. Deep debiased contrastive hashing. Pattern Recognition, 2023, 139: 109483.
    [13] Chuang CY, Robinson J, Lin YC, et al. Debiased contrastive learning. Proceedings of the 34th International Conference on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2020. 735.
    [14] Wang JP, Zeng ZY, Chen B, et al. Contrastive quantization with code memory for unsupervised image retrieval. Proceedings of the 36th AAAI Conference on Artificial Intelligence. AAAI Press, 2022. 2468–2476.
    [15] Dai B, Guo RQ, Kumar S, et al. Stochastic generative hashing. Proceedings of the 34th International Conference on Machine Learning. Sydney: PMLR, 2017. 913–922.
    [16] Shen YM, Liu L, Shao L. Unsupervised binary representation learning with deep variational networks. International Journal of Computer Vision, 2019, 127(11-12): 1614–1628.
    [17] Do TT, Doan AD, Cheung NM. Learning to hash with binary deep neural network. Proceedings of the 14th European Conference on Computer Vision. Amsterdam: Springer, 2016. 219–234.
    [18] Shen YM, Qin J, Chen JX, et al. Auto-encoding twin-bottleneck hashing. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 2818–2827.
    [19] Dizaji KG, Zheng F, Sadoughi Nourabadi N, et al. Unsupervised deep generative adversarial hashing network. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018. 3664–3673.
    [20] Lin K, Lu JW, Chen CS, et al. Learning compact binary descriptors with unsupervised deep neural networks. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016. 1183–1192.
    [21] Yang EK, Deng C, Liu TL, et al. Semantic structure-based unsupervised deep hashing. Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm: AAAI Press, 2018. 1064–1070.
    [22] Lin QH, Chen XJ, Zhang Q, et al. Deep unsupervised hashing with latent semantic components. Proceedings of the 36th AAAI Conference on Artificial Intelligence. AAAI Press, 2022. 7488–7496.
    [23] Wu ZR, Xiong YJ, Yu SX, et al. Unsupervised feature learning via non-parametric instance discrimination. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018. 3733–3742.
    [24] Ye M, Zhang X, Yuen PC, et al. Unsupervised embedding learning via invariant and spreading instance feature. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 6210–6219.
    [25] He KM, Fan HQ, Wu YX, et al. Momentum contrast for unsupervised visual representation learning. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 9729–9738.
    [26] Misra I, van der Maaten L. Self-supervised learning of pretext-invariant representations. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 6707–6717.
    [27] Zhuang CX, Zhai A, Yamins D. Local aggregation for unsupervised learning of visual embeddings. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019. 6002–6012.
    [28] Hjelm RD, Fedorov A, Lavoie-Marchildon S, et al. Learning deep representations by mutual information estimation and maximization. Proceedings of the 7th International Conference on Learning Representations. New Orleans: OpenReview.net, 2019.
    [29] van den Oord A, Li YZ, Vinyals O. Representation learning with contrastive predictive coding. arXiv:1807.03748, 2018.
    [30] Tian YL, Krishnan D, Isola P. Contrastive multiview coding. Proceedings of the 16th European Conference on Computer Vision. Glasgow: Springer, 2020. 776–794.
    [31] Cai TT, Frankle J, Schwab DJ, et al. Are all negatives created equal in contrastive instance discrimination? arXiv:2010.06682, 2020.
    [32] Yuan L, Wang T, Zhang XP, et al. Central similarity quantization for efficient image and video retrieval. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 3083–3092.
    [33] Song JK, He T, Gao LL, et al. Binary generative adversarial networks for image retrieval. Proceedings of the 32nd AAAI Conference on Artificial Intelligence. New Orleans: AAAI Press, 2018. 394–401.
    [34] Yang EK, Liu TL, Deng C, et al. DistillHash: Unsupervised deep hashing by distilling data pairs. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 2946–2955.
    [35] Meng LT, Zhang QY, Yang R, et al. Unsupervised deep triplet hashing for image retrieval. IEEE Signal Processing Letters, 2024, 31: 1489–1493.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

苏海,钟雨辰.基于偏差抑制对比学习的无监督深度哈希图像检索.计算机系统应用,2025,34(2):165-173

Copy
Share
Article Metrics
  • Abstract:114
  • PDF: 326
  • HTML: 78
  • Cited by: 0
History
  • Received:July 29,2024
  • Revised:August 20,2024
  • Online: December 16,2024
Article QR Code
You are the first991200Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-3
Address:4# South Fourth Street, Zhongguancun,Haidian, Beijing,Postal Code:100190
Phone:010-62661041 Fax: Email:csa (a) iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063