HashNet: Deep Learning to Hash by Continuation
Open accessAbstract
Learning to hash has been widely applied to approximate nearest neighbor search for large-scale multimedia retrieval, due to its computation efficiency and retrieval quality. Deep learning to hash, which improves retrieval quality by end-to-end representation learning and hash encoding, has received increasing attention recently. Subject to the ill-posed gradient difficulty in the optimization with sign activations, existing deep learning to hash methods need to first learn continuous representations and then generate binary hash codes in a separated binarization step, which suffer from substantial loss of retrieval quality. This work presents HashNet, a novel deep architecture for deep learning to hash by continuation method with convergence guarantees, which learns exactly binary hash codes from imbalanced similarity data. The key idea is to attack the ill-posed gradient problem in optimizing deep networks with non-smooth binary activations by continuation method, in which we begin from learning an easier network with smoothed activation function and let it evolve during the training, until it eventually goes back to being the original, difficult to optimize, deep network with the sign activation function. Comprehensive empirical evidence shows that HashNet can generate exactly binary hash codes and yield state-of-the-art multimedia retrieval performance on standard benchmarks.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460 · see citing works
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · see citing works
(2014) · Cited by 33,419 · see citing works
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · see citing works
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · see citing works
(2010) · International Conference on Machine Learning · Cited by 13,995 · see citing works
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · see citing works
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077 · see citing works
Content-based image retrieval at the end of the early years
Smeulders, A. W. M., Worring, M., Santini, S., Gupta, A., & Jain, R. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.895972 · Cited by 6,050 · see citing works
Greedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841 · see citing works
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · see citing works
(1999) · Cited by 3,186 · see citing works
NUS-WIDE: a real-world web image database from National University of Singapore
Chua, T.-S., Tang, J., Hong, R., Li, H., Luo, Z., & Zheng, Y. (2009) · Proceedings of the ACM International Conference on Image and Video Retrieval · doi:10.1145/1646396.1646452 · Cited by 3,025 · see citing works
Product Quantization for Nearest Neighbor Search
Jégou, H., Douze, M., & Schmid, C. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.57 · Cited by 2,956 · cited 1× · see citing works
“Typical learning criteria include reconstruction error minimization [30, 12, 16] and graph learning[36, 24].”
BackgroundWeiss, Y., Torralba, A. B., & Fergus, R. (2008) · neural information processing systems · Cited by 2,389 · see citing works
Content-based multimedia information retrieval: State of the art and challenges
Lew, M. S., Sebe, N., Djeraba, C., & Jain, R. (2006) · ACM Transactions on Multimedia Computing, Communications, and Applications · doi:10.1145/1126004.1126005 · Cited by 1,528 · see citing works
Supervised hashing with kernels
Liu, W., Wang, J., Ji, R., Jiang, Y., & Chang, S. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247912 · Cited by 1,418 · see citing works
Self-citationShen, F., Shen, C., Liu, W., & Shen, H. T. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298598 · Cited by 1,258 · see citing works
Iterative quantization: A procrustean approach to learning binary codes
Gong, Y., & Lazebnik, S. (2011) · doi:10.1109/cvpr.2011.5995432 · Cited by 1,089 · see citing works
Numerical Continuation Methods--An Introduction.
Watson, L. T., Allgower, E. L., & Georg, K. (1992) · Mathematics of Computation · doi:10.2307/2153001 · Cited by 1,016 · see citing works
Supervised Hashing for Image Retrieval via Image Representation Learning
Xia, R., Pan, Y., Lai, H., Liu, C., & Yan, S. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8952 · Cited by 980 · see citing works
Deep Supervised Hashing for Fast Image Retrieval
Liu, H., Wang, R., Shan, S., & Chen, X. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.227 · Cited by 933 · see citing works
Simultaneous feature learning and hash coding with deep neural networks
Lai, H., Pan, Y., Liu, Y., & Yan, S. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298947 · Cited by 884 · see citing works
Learning to Hash with Binary Reconstructive Embeddings
Kulis, B., & Darrell, T. (2009) · Cited by 806 · see citing works
Semi-Supervised Hashing for Large-Scale Search
Wang, J., Kumar, S., & Chang, S. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.48 · Cited by 805 · see citing works
Self-citationMinimal Loss Hashing for Compact Binary Codes
Norouzi, M., & Blei, D. M. (2011) · Cited by 695 · see citing works
Deep Hashing Network for Efficient Similarity Retrieval
Zhu, H., Long, M., Wang, J., & Cao, Y. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10235 · Cited by 664 · see citing works
Self-citationDeep semantic ranking based hashing for multi-label image retrieval
Zhao, F. P., Huang, Y., Wang, L., & Tan, T. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298763 · Cited by 574 · see citing works
Hamming Distance Metric Learning
Norouzi, M., Fleet, D. J., & Salakhutdinov, R. (2012) · Cited by 562 · see citing works
Deep hashing for compact binary codes learning
Liong, V. E., Lu, J., Wang, G., Moulin, P., & Zhou, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298862 · Cited by 545 · see citing works
V0.1ICPreprint
Radisic, A. (2025) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.17117444 · Cited by 495 · see citing works
BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1Preprint
Courbariaux, M., & Bengio, Y. (2016) · arXiv (Cornell University) · Cited by 484 · see citing works
Hashing for Similarity Search: A SurveyPreprint
Wang, J., Shen, H. T., Song, J., & Ji, J. (2014) · arXiv (Cornell University) · doi:10.4230/lipics.cpm.2023.20 · Cited by 458 · see citing works
Self-citationLearning a Nonlinear Embedding by Preserving Class Neighbourhood Structure
Salakhutdinov, R., & Hinton, G. E. (2007) · Cited by 437 · see citing works
Supervised hashing with latent factor models
Zhang, P., Zhang, W., Li, W.-J., & Guo, M. (2014) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2600428.2609600 · Cited by 276 · see citing works
Fast search in Hamming space with multi-index hashing
Norouzi, M., Punjani, A., & Fleet, D. J. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6248043 · Cited by 263 · see citing works
Learning Binary Codes for High-Dimensional Data Using Bilinear Projections
Gong, Y., Kumar, S., Rowley, H. A., & Lazebnik, S. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.69 · Cited by 164 · see citing works
Circulant Binary EmbeddingPreprint
Yu, F., Kumar, S., Gong, Y., & Chang, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.3162 · Cited by 154 · see citing works
Hash Bit Selection: A Unified Solution for Selection Problems in Hashing
Liu, X., He, J., Lang, B., & Chang, S. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.206 · Cited by 89 · see citing works
Maximum Likelihood in Cost-Sensitive Learning: Model Specification, Approximations, and Upper Bounds
Dmochowski, J., Sajda, P., & Parra, L. C. (2010) · doi:10.5555/1756006.1953037 · Cited by 63 · see citing works
Partial Hash Update via Hamming Subspace Learning
Ma, C., Tsang, I. W.-H., Peng, F., & Liu, C. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2675342 · Cited by 11 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Douze, M., Guzhva, A., Deng, C., Johnson, J., Szilvasy, G., Mazaré, P.-E., Lomeli, M., Hosseini, L., & Jégou, H. (2026) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2025.3618474 · Cited by 478 · see citing works
Central Similarity Quantization for Efficient Image and Video Retrieval
Yuan, L., Wang, T., Zhang, X., Tay, F. E., Jie, Z., Liu, W., & Feng, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00315 · Cited by 413 · see citing works
COOKIE: Contrastive Cross-Modal Knowledge Sharing Pre-training for Vision-Language Representation
Wen, K., Xia, J., Huang, Y., Li, L., Xu, J., & Shao, J. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00221 · Cited by 37 · see citing works
Deep Perceptual Hash Based on Hash Center for Image Copyright Protection
Sun, X., & Zhou, J. (2022) · IEEE Access · doi:10.1109/access.2022.3221980 · Cited by 20 · see citing works
“The representative ones are DSH [29], DPSH [30], HashNet [31], ADSH [32] etc.”
Background
- Authors
- Cao, Z., Long, M., Wang, J., & Yu, P. S.
- Affiliations
- Tsinghua University (CN)
- University of Illinois Chicago (US)
- Venue
- 2017 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 5609-5618
- OpenAlex
- W2964280870
- Cited by
- 777
- References
- 43
- Citations by year
- 2026: 40 · 2025: 80 · 2024: 86 · 2023: 119 · 2022: 100 · 2021: 108 · 2020: 98 · 2019: 91 · 2018: 53 · 2017: 2
- FWCI
- 19.51
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (61325008, 71690231, 61502265, 2015BAF32B01)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- binary hash codes, numerical continuation, approximate nearest neighbor search, multimedia retrieval
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
