# Learning to Hash with Binary Deep Neural Network

arXiv: https://arxiv.org/abs/1607.05140 · HTML: https://mlsanity.com/paper/1607.05140/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2016.

## Built on by (most cited first, 13 of 13)

- [Unsupervised Hashing with Contrastive Information Bottleneck](https://mlsanity.com/paper/2105.06138/) (2021)
- [One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching](https://mlsanity.com/paper/2205.15721/) (2022)
- [HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation](https://mlsanity.com/paper/2505.16133/) (2025)
- [Unsupervised Representation Learning via Neural Activation Coding](https://mlsanity.com/paper/2112.04014/) (2021)
- [DeepLSH: Deep Locality-Sensitive Hash Learning for Fast and Efficient Near-Duplicate Crash Report Detection](https://mlsanity.com/paper/2310.06703/) (2023)
- [A Domain-Oblivious Approach for Learning Concise Representations of Filtered Topological Spaces for Clustering](https://mlsanity.com/paper/2105.12208/) (2021)
- [Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings](https://mlsanity.com/paper/2609.03376/) (2026)
- [Training Multilayer Perceptrons by Sampling with Quantum Annealers](https://mlsanity.com/paper/2303.12352/) (2023)
- [Online Hashing with Similarity Learning](https://mlsanity.com/paper/2108.02560/) (2021)
- [Unsupervised Domain-adaptive Hash for Networks](https://mlsanity.com/paper/2108.09136/) (2021)
- [Beyond Neighbourhood-Preserving Transformations for Quantization-Based Unsupervised Hashing](https://mlsanity.com/paper/2110.00216/) (2021)
- [Supervised Auto-Encoding Twin-Bottleneck Hashing](https://mlsanity.com/paper/2306.11122/) (2023)
- [GARLIC: GAussian Representation LearnIng for spaCe partitioning](https://mlsanity.com/paper/2505.24608/) (2025)

## Abstract (arXiv)

This work proposes deep network models and learning algorithms for unsupervised and supervised binary hashing. Our novel network design constrains one hidden layer to directly output the binary codes. This addresses a challenging issue in some previous works: optimizing non-smooth objective functions due to binarization. Moreover, we incorporate independence and balance properties in the direct and strict forms in the learning. Furthermore, we include similarity preserving property in our objective function. Our resulting optimization with these binary, independence, and balance constraints is difficult to solve. We propose to attack it with alternating optimization and careful relaxation. Experimental results on three benchmark datasets show that our proposed methods compare favorably with the state of the art.