# DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs

arXiv: https://arxiv.org/abs/1905.03465 · HTML: https://mlsanity.com/paper/1905.03465/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2019.

## Built on by (most cited first, 26 of 26)

- [SimMatch: Semi-supervised Learning with Similarity Matching](https://mlsanity.com/paper/2203.06915/) (2022)
- [Self-supervised Product Quantization for Deep Unsupervised Image Retrieval](https://mlsanity.com/paper/2109.02244/) (2021)
- [Unsupervised Hashing with Contrastive Information Bottleneck](https://mlsanity.com/paper/2105.06138/) (2021)
- [Contrastive Quantization with Code Memory for Unsupervised Image Retrieval](https://mlsanity.com/paper/2109.05205/) (2021)
- [Deep Hash Distillation for Image Retrieval](https://mlsanity.com/paper/2112.08816/) (2021)
- [One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching](https://mlsanity.com/paper/2205.15721/) (2022)
- [Hyperbolic Hierarchical Contrastive Hashing](https://mlsanity.com/paper/2212.08904/) (2022)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [NeuroHash: A Hyperdimensional Neuro-Symbolic Framework for Spatially-Aware Image Hashing and Retrieval](https://mlsanity.com/paper/2404.11025/) (2024)
- [Unsupervised Hashing with Semantic Concept Mining](https://mlsanity.com/paper/2209.11475/) (2022)
- [Unsupervised Representation Learning via Neural Activation Coding](https://mlsanity.com/paper/2112.04014/) (2021)
- [Learning to Hash Naturally Sorts](https://mlsanity.com/paper/2201.13322/) (2022)
- [Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval](https://mlsanity.com/paper/2310.08009/) (2023)
- [Deep Self-Adaptive Hashing for Image Retrieval](https://mlsanity.com/paper/2108.07094/) (2021)
- [Deep Hashing with Semantic Hash Centers for Image Retrieval](https://mlsanity.com/paper/2507.08404/) (2025)
- [Dual Learning with Dynamic Knowledge Distillation and Soft Alignment for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2510.12283/) (2025)
- [DVHN: A Deep Hashing Framework for Large-scale Vehicle Re-identification](https://mlsanity.com/paper/2112.04937/) (2021)
- [Unsupervised Hashing with Similarity Distribution Calibration](https://mlsanity.com/paper/2302.07669/) (2023)
- [Weighted Contrastive Hashing](https://mlsanity.com/paper/2209.14099/) (2022)
- [CoopHash: Cooperative Learning of Multipurpose Descriptor and Contrastive Pair Generator via Variational MCMC Teaching for Supervised Image Hashing](https://mlsanity.com/paper/2210.04288/) (2022)
- [Leveraging High-Resolution Features for Improved Deep Hashing-based Image Retrieval](https://mlsanity.com/paper/2403.13747/) (2024)
- [DAC: 2D-3D Retrieval with Noisy Labels via Divide-and-Conquer Alignment and Correction](https://mlsanity.com/paper/2407.17779/) (2024)
- [From Image Hashing to Scene Change Detection](https://mlsanity.com/paper/2605.12259/) (2026)
- [Deep Unsupervised Hashing by Distilled Smooth Guidance](https://mlsanity.com/paper/2105.06125/) (2021)
- [Self-Supervised Consistent Quantization for Fully Unsupervised Image Retrieval](https://mlsanity.com/paper/2206.09806/) (2022)
- [Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing](https://mlsanity.com/paper/2403.06071/) (2024)

## Abstract (arXiv)

Due to the high storage and search efficiency, hashing has become prevalent for large-scale similarity search. Particularly, deep hashing methods have greatly improved the search performance under supervised scenarios. In contrast, unsupervised deep hashing models can hardly achieve satisfactory performance due to the lack of reliable supervisory similarity signals. To address this issue, we propose a novel deep unsupervised hashing model, dubbed DistillHash, which can learn a distilled data set consisted of data pairs, which have confidence similarity signals. Specifically, we investigate the relationship between the initial noisy similarity signals learned from local structures and the semantic similarity labels assigned by a Bayes optimal classifier. We show that under a mild assumption, some data pairs, of which labels are consistent with those assigned by the Bayes optimal classifier, can be potentially distilled. Inspired by this fact, we design a simple yet effective strategy to distill data pairs automatically and further adopt a Bayesian learning framework to learn hash functions from the distilled data set. Extensive experimental results on three widely used benchmark datasets show that the proposed DistillHash consistently accomplishes the state-of-the-art search performance.