| Citation: | SHAO W Z，XIONG S Y，PAN L L. Semi-supervised image retrieval based on triplet hash loss[J]. Journal of Beijing University of Aeronautics and Astronautics，2025，51（7）：2526-2537 （in Chinese） doi: 10.13700/j.bh.1001-5965.2023.0451
|
Currently, most of the image retrieval methods based on deep learning are supervised techniques, which require massive labeled data. However, it is very difficult and expensive to label so much data in real applications. Furthermore, the network learned picture similarity poorly since the triple loss functions that were in place were computed using Euclidean distance. In this work, a novel semi-supervised hash image retrieval model (SSITL) is proposed that mixes the pseudo-labels with entropy minimization, triplet hash loss and semi-supervised learning. The multi-stage model union and sharpening technique are used to generate pseudo-labels, and the pseudo-labels are processed with entropy minimization to improve their confidence. The triplet hash loss based on the channel weight matrix is utilized to assist SSITL in learning the similarity of images, while the triples are chosen concurrently depending on the clustering outcomes of labeled and unlabeled data. In order to generate a better hash code, Mix Up is used to shuffle between two Hamming embeddings to obtain a new Hamming embedding for image retrieval. The abundant experimental results show that compared with other methods, SSITL improves the average retrieval accuracy by 1.2% and 0.7% respectively on CIFAR-10 and NUS-WIDE datasets under similar time cost, which strongly demonstrates that SSITL is an excellent semi-supervised hash framework for image retrieval.
| [1] |
LI W, DUAN L X, XU D, et al. Text-based image retrieval using progressive multi-instance learning[C]//Proceedings of the 2011 International Conference on Computer Vision. Piscataway: IEEE Press, 2011: 2049-2055.
|
| [2] |
LIU Y, ZHANG D S, LU G J, et al. A survey of content-based image retrieval with high-level semantics[J]. Pattern Recognition, 2007, 40(1): 262-282. doi: 10.1016/j.patcog.2006.04.045
|
| [3] |
CHEN R Y, PAN L L, LI C, et al. An improved deep fusion CNN for image recognition[J]. Computers, Materials & Continua, 2020, 65(2): 1691-1706.
|
| [4] |
LAI H J, PAN Y, YE L, et al. Simultaneous feature learning and hash coding with deep neural networks[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2015: 3270-3278.
|
| [5] |
CHEN Y B, MANCINI M, ZHU X T, et al. Semi-supervised and unsupervised deep visual learning: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(3): 1327-1347. doi: 10.1109/TPAMI.2022.3201576
|
| [6] |
刘颖, 程美, 王富平, 等. 深度哈希图像检索方法综述[J]. 中国图象图形学报, 2020, 25(7): 1296-1317. doi: 10.11834/jig.190518
LIU Y, CHENG M, WANG F P, et al. Deep Hashing image retrieval methods[J]. Journal of Image and Graphics, 2020, 25(7): 1296-1317(in Chinese). doi: 10.11834/jig.190518
|
| [7] |
ZHU X, GOLDBERG A B. Introduction to semi-supervised learning[J]. Synthesis Lectures on Artificial Intelligence and Machine Learning, 2009, 3(1): 1-130.
|
| [8] |
SCHROFF F, KALENICHENKO D, PHILBIN J. FaceNet: a unified embedding for face recognition and clustering[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2015: 815-823.
|
| [9] |
SONG H O, XIANG Y, JEGELKA S, et al. Deep metric learning via lifted structured feature embedding[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2016: 4004-4012.
|
| [10] |
郑大刚, 刘光杰, 茅耀斌, 等. 基于三元组损失函数的深度人脸哈希方法[J]. 太赫兹科学与电子信息学报, 2021, 19(2): 313-318. doi: 10.11805/TKYDA2018108
ZHENG D G, LIU G J, MAO Y B, et al. Deep face Hashing based on ternary-group loss function[J]. Journal of Terahertz Science and Electronic Information Technology, 2021, 19(2): 313-318(in Chinese). doi: 10.11805/TKYDA2018108
|
| [11] |
杜雨佳, 李海生, 姚春莲, 等. 基于三元组网络的单图三维模型检索[J]. 北京亚洲成人在线一二三四五六区学报, 2020, 46(9): 1691-1700.
DU Y J, LI H S, YAO C L, et al. Monocular image based 3D model retrieval using triplet network[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(9): 1691-1700(in Chinese).
|
| [12] |
刘晗煜, 黄宏恩, 郑世宝. 基于视角一致性三元组损失的车辆重识别技术[J]. 测控技术, 2021, 40(8): 47-53,63.
LIU H Y, HUANG H E, ZHENG S B. View consistency triplet loss for vehicle re-identification[J]. Measurement & Control Technology, 2021, 40(8): 47-53,63 (in Chinese).
|
| [13] |
LIAO S C, SHAO L. Graph sampling based deep metric learning for generalizable person re-identification[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2022: 7349-7358.
|
| [14] |
YANG S, ZHANG Y F, ZHAO Q H, et al. Prototype-based support example miner and triplet loss for deep metric learning[J]. Electronics, 2023, 12(15): 3315. doi: 10.3390/electronics12153315
|
| [15] |
LI Z, KO B, CHOI H J. Naive semi-supervised deep learning using pseudo-label[J]. Peer-to-Peer Networking and Applications, 2019, 12(5): 1358-1368. doi: 10.1007/s12083-018-0702-9
|
| [16] |
BERTHELOT D, CARLINI N, GOODFELLOW I, et al. MixMatch: a holistic approach to semi-supervised learning[EB/OL]. (2019-10-23)[2023-05-23]. http://doi.org/10.48550/arXiv.1905.02249.
|
| [17] |
ZHANG J, PENG Y X. SSDH: Semi-supervised deep hashing for large scale image retrieval[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 29(1): 212-225.
|
| [18] |
GUO Z T, HONG C Q, ZHUANG W W, et al. CPQN: central product quantization network for semi-supervised image retrieval[C]//Proceedings of the 2021 IEEE International Conference on Big Data. Piscataway: IEEE Press, 2021: 3183-3190.
|
| [19] |
WANG G A, HU Q H, YANG Y, et al. Adversarial binary mutual learning for semi-supervised deep hashing[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(8): 4110-4124. doi: 10.1109/TNNLS.2021.3055834
|
| [20] |
魏翔, 王靖杰, 张顺利, 等. ReLSL: 基于可靠标签选择与学习的半监督学习算法[J]. 计算机学报, 2022, 45(6): 1147-1160. doi: 10.11897/SP.J.1016.2022.01147
WEI X, WANG J J, ZHANG S L, et al. ReLSL: reliable label selection and learning based algorithm for semi-supervised learning[J]. Chinese Journal of Computers, 2022, 45(6): 1147-1160(in Chinese). doi: 10.11897/SP.J.1016.2022.01147
|
| [21] |
ZHANG H Y, CISSE M, DAUPHIN Y N, et al. Mixup: beyond empirical risk minimization[EB/OL]. (2018-04-27)[2023-05-25]. http://doi.org/10.48550/arXiv.1710.09412.
|
| [22] |
WANG G A, HU Q H, YANG Y, et al. Adversarial binary mutual learning for semi-supervised deep hashing[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 33(8): 4110-4124.
|
| [23] |
KRIZHEVSKY A, HINTON G. Convolutional deep belief networks on cifar-10[J]. Unpublished Manuscript, 2010, 40(7): 1-9.
|
| [24] |
CHUA T S, TANG J H, HONG R C, et al. NUS-WIDE: a real-world web image database from National University of Singapore[C]// Proceedings of the ACM International Conference on Image and Video Retrieval. New York: ACM, 2009: 1-9.
|
| [25] |
SHEN F M, SHEN C H, LIU W, et al. Supervised discrete hashing[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2015: 37-45.
|
| [26] |
GONG Y C, LAZEBNIK S, GORDO A, et al. Iterative quantization: a Procrustean approach to learning binary codes for large-scale image retrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 35(12): 2916-2929.
|
| [27] |
LI W J, WANG S, KANG W C. Feature learning based deep supervised hashing with pairwise labels[EB/OL]. (2016-04-21)[2023-05-27]. http://doi.org/10.48550/arXiv.1511.03855.
|
| [28] |
ZHANG R M, LIN L, ZHANG R, et al. Bit-scalable deep hashing with regularized similarity learning for image retrieval and person re-identification[J]. IEEE Transactions on Image Processing, 2015, 24(12): 4766-4779. doi: 10.1109/TIP.2015.2467315
|
| [29] |
LI Q, SUN Z, HE R, et al. Deep supervised discrete hashing[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: Curran Associates, 2017: 2479-2488.
|
| [30] |
YAN X, ZHANG L, LI W J. Semi-supervised deep Hashing with a bipartite graph[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence. Melbourne: IJCAJ, 2017: 3238-3244.
|
| [31] |
QIU Z F, PAN Y W, YAO T, et al. Deep semantic hashing with generative adversarial networks[C]// Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2017: 225-234.
|
| [32] |
WANG G A, HU Q H, CHENG J, et al. Semi-supervised generative adversarial hashing for image retrieval[C]// Computer Vision – ECCV 2018. Berlin: Springer, 2018: 491-507.
|
Figures(8) / Tables(10)
Copyright © Journal of Beijing University of Aeronautics and Astronautics
Address: Editorial Department of Journal of Beijing University of Aeronautics and Astronautics, 37 Xueyuan Road, Haidian District, Beijing Post Code: 100191 Email: jbuaa@cqjj8.com
Supported by:
Beijing Renhe Information Technology Co., Ltd.
DownLoad:
