# Hashing with Binary Matrix Pursuit

arXiv: https://arxiv.org/abs/1808.01990 · HTML: https://mlsanity.com/paper/1808.01990/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2018.

## Built on by (most cited first, 4 of 4)

- [SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval](https://mlsanity.com/paper/2209.13833/) (2022)
- [Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization](https://mlsanity.com/paper/2607.06922/) (2026)
- [Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization](https://mlsanity.com/paper/2509.17049/) (2025)
- [Supervised Auto-Encoding Twin-Bottleneck Hashing](https://mlsanity.com/paper/2306.11122/) (2023)

## Abstract (arXiv)

We propose theoretical and empirical improvements for two-stage hashing methods. We first provide a theoretical analysis on the quality of the binary codes and show that, under mild assumptions, a residual learning scheme can construct binary codes that fit any neighborhood structure with arbitrary accuracy. Secondly, we show that with high-capacity hash functions such as CNNs, binary code inference can be greatly simplified for many standard neighborhood definitions, yielding smaller optimization problems and more robust codes. Incorporating our findings, we propose a novel two-stage hashing method that significantly outperforms previous hashing studies on widely used image retrieval benchmarks.