mlsanityData to 7 Oct 2026

A Survey on Learning to Hash

arXiv 1606.00185 ↗First posted 1 Jun 2016cs.CVcited by 119

Not on the map. Why?

Abstract (arXiv)

Nearest neighbor search is a problem of finding the data points from the database such that the distances from them to the query point are the smallest. Learning to hash is one of the major solutions to this problem and has been widely studied recently. In this paper, we present a comprehensive survey of the learning to hash algorithms, categorize them according to the manners of preserving the similarities into: pairwise similarity preserving, multiwise similarity preserving, implicit similarity preserving, as well as quantization, and discuss their relations. We separate quantization from pairwise similarity preserving as the objective function is very different though quantization, as we show, can be derived from preserving the pairwise similarities. In addition, we present the evaluation protocols, and the general performance analysis, and point out that the quantization algorithms perform superiorly in terms of search accuracy, search time cost, and space cost. Finally, we introduce a few emerging topics.

Key facts. Cited by 119 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 26; 2023: 22; 2024: 8; 2025: 17; 2026: 10.

119 papers.

Sort:

By area:

  1. 2024The Faiss librarycited by 370
  2. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  3. 2025TurboQuant: Online Vector Quantization with Near-optimal Distortion Ratecited by 116
  4. 2022Learning Vector-Quantized Item Representation for Transferable Sequential Recommenderscited by 112
  5. 2021Where is your place, Visual Place Recognition?cited by 82
  6. 2021Deep Learning for Instance Retrieval: A Surveycited by 70
  7. 2021Efficient Passage Retrieval with Hashing for Open-domain Question Answeringcited by 53
  8. 2022Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Searchcited by 45
  9. 2021One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objectivecited by 43
  10. 2021SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Searchcited by 35
  11. 2022A Comprehensive Survey on Trustworthy Recommender Systemscited by 32
  12. 2021Self-supervised Product Quantization for Deep Unsupervised Image Retrievalcited by 28
38 more
  1. 2022BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Labelcited by 28
  2. 2022A Survey for Efficient Open Domain Question Answeringcited by 20
  3. 2023Similarity search in the blink of an eye with compressed indicescited by 20
  4. 2023Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitationscited by 20
  5. 2025Enhancing Embedding Representation Stability in Recommendation Systems with Semantic IDcited by 19
  6. 2021Neural Distance Embeddings for Biological Sequencescited by 17
  7. 2021MOTIF: A Large Malware Reference Dataset with Ground Truth Family Labelscited by 17
  8. 2025A Comprehensive Survey on Composed Image Retrievalcited by 17
  9. 2021Contrastive Quantization with Code Memory for Unsupervised Image Retrievalcited by 16
  10. 2021Towards Visual Semanticscited by 12
  11. 2022SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrievalcited by 11
  12. 2022ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretizationcited by 10
  13. 2022HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learningcited by 10
  14. 2024Locally-Adaptive Quantization for Streaming Vector Searchcited by 10
  15. 2021Deep Hash Distillation for Image Retrievalcited by 9
  16. 2022One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matchingcited by 9
  17. 2022Learning Binary and Sparse Permutation-Invariant Representations for Fast and Memory Efficient Whole Slide Image Searchcited by 9
  18. 2022Hyperbolic Hierarchical Contrastive Hashingcited by 9
  19. 2021Deep Triplet Hashing Network for Case-based Medical Image Retrievalcited by 8
  20. 2021Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashingcited by 8
  21. 2022Hybrid Contrastive Quantization for Efficient Cross-View Video Retrievalcited by 8
  22. 2023Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrievalcited by 8
  23. 2025PDX: A Data Layout for Vector Similarity Searchcited by 8
  24. 2021Semi-supervised Network Embedding with Differentiable Deep Quantisationcited by 7
  25. 2021For Manifold Learning, Deep Neural Networks can be Locality Sensitive Hash Functionscited by 6
  26. 2021Instance-weighted Central Similarity for Multi-label Image Retrievalcited by 6
  27. 2023SEM-POS: Grammatically and Semantically Correct Video Captioningcited by 6
  28. 2025DarkHash: A Data-Free Backdoor Attack Against Deep Hashingcited by 6
  29. 2021Unsupervised Multi-Index Semantic Hashingcited by 5
  30. 2022Deep Partial Multiplex Network Embeddingcited by 5
  31. 2023An Efficient Content-based Time Series Retrieval Systemcited by 5
  32. 2023Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrievalcited by 5
  33. 2023Attributes Grouping and Mining Hashing for Fine-Grained Image Retrievalcited by 5
  34. 2023LeanVec: Searching vectors faster by making them fitcited by 5
  35. 2024BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilitiescited by 5
  36. 2025HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generationcited by 5
  37. 2021Neural networks behave as hash encoders: An empirical studycited by 3
  38. 2021Deep Self-Adaptive Hashing for Image Retrievalcited by 3

50 most cited of 119 All 119 (JSON)