# Hashing with binary autoencoders

arXiv: https://arxiv.org/abs/1501.00756 · HTML: https://mlsanity.com/paper/1501.00756/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jan 2015.

## Built on by (most cited first, 9 of 9)

- [LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes](https://mlsanity.com/paper/2106.01487/) (2021)
- [Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling](https://mlsanity.com/paper/2107.04312/) (2021)
- [Logarithmic Continual Learning](https://mlsanity.com/paper/2201.06534/) (2022)
- [Unsupervised Hashing with Similarity Distribution Calibration](https://mlsanity.com/paper/2302.07669/) (2023)
- [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)
- [HyBNN and FedHyBNN: (Federated) Hybrid Binary Neural Networks](https://mlsanity.com/paper/2205.09839/) (2022)
- [Sparse-Inductive Generative Adversarial Hashing for Nearest Neighbor Search](https://mlsanity.com/paper/2306.06928/) (2023)
- [Learning Binary Autoencoder-Based Codes with Progressive Training](https://mlsanity.com/paper/2511.09221/) (2025)

## Abstract (arXiv)

An attractive approach for fast search in image databases is binary hashing, where each high-dimensional, real-valued image is mapped onto a low-dimensional, binary vector and the search is done in this binary space. Finding the optimal hash function is difficult because it involves binary constraints, and most approaches approximate the optimization by relaxing the constraints and then binarizing the result. Here, we focus on the binary autoencoder model, which seeks to reconstruct an image from the binary code produced by the hash function. We show that the optimization can be simplified with the method of auxiliary coordinates. This reformulates the optimization as alternating two easier steps: one that learns the encoder and decoder separately, and one that optimizes the code for each image. Image retrieval experiments, using precision/recall and a measure of code utilization, show the resulting hash function outperforms or is competitive with state-of-the-art methods for binary hashing.