# BinGAN: Learning Compact Binary Descriptors with a Regularized GAN

arXiv: https://arxiv.org/abs/1806.06778 · HTML: https://mlsanity.com/paper/1806.06778/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2018.

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

- [Self-supervised Product Quantization for Deep Unsupervised Image Retrieval](https://mlsanity.com/paper/2109.02244/) (2021)
- [Local Feature Matching Using Deep Learning: A Survey](https://mlsanity.com/paper/2401.17592/) (2024)
- [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)
- [Selectively increasing the diversity of GAN-generated samples](https://mlsanity.com/paper/2207.01561/) (2022)
- [Hyperbolic Hierarchical Contrastive Hashing](https://mlsanity.com/paper/2212.08904/) (2022)
- [ViT2Hash: Unsupervised Information-Preserving Hashing](https://mlsanity.com/paper/2201.05541/) (2022)
- [Learning to Hash Naturally Sorts](https://mlsanity.com/paper/2201.13322/) (2022)
- [Unsupervised Hashing with Similarity Distribution Calibration](https://mlsanity.com/paper/2302.07669/) (2023)
- [Weighted Contrastive Hashing](https://mlsanity.com/paper/2209.14099/) (2022)
- [From Image Hashing to Scene Change Detection](https://mlsanity.com/paper/2605.12259/) (2026)
- [Self-Supervised Consistent Quantization for Fully Unsupervised Image Retrieval](https://mlsanity.com/paper/2206.09806/) (2022)
- [Sparse-Inductive Generative Adversarial Hashing for Nearest Neighbor Search](https://mlsanity.com/paper/2306.06928/) (2023)

## Abstract (arXiv)

In this paper, we propose a novel regularization method for Generative Adversarial Networks, which allows the model to learn discriminative yet compact binary representations of image patches (image descriptors). We employ the dimensionality reduction that takes place in the intermediate layers of the discriminator network and train binarized low-dimensional representation of the penultimate layer to mimic the distribution of the higher-dimensional preceding layers. To achieve this, we introduce two loss terms that aim at: (i) reducing the correlation between the dimensions of the binarized low-dimensional representation of the penultimate layer i. e. maximizing joint entropy) and (ii) propagating the relations between the dimensions in the high-dimensional space to the low-dimensional space. We evaluate the resulting binary image descriptors on two challenging applications, image matching and retrieval, and achieve state-of-the-art results.