# Sparse-Inductive Generative Adversarial Hashing for Nearest Neighbor Search

arXiv: https://arxiv.org/abs/2306.06928 · HTML: https://mlsanity.com/paper/2306.06928/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 12 Jun 2023.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Compressed Sensing using Generative Models](https://mlsanity.com/paper/1703.03208/) (2017)
- [Learning Discrete Representations via Information Maximizing Self-Augmented Training](https://mlsanity.com/paper/1702.08720/) (2017)
- [A Survey on Learning to Hash](https://mlsanity.com/paper/1606.00185/) (2016)
- [Energy-based Generative Adversarial Network](https://mlsanity.com/paper/1609.03126/) (2016)
- [Convolutional Networks with Dense Connectivity](https://mlsanity.com/paper/2001.02394/) (2020)
- [SpectralNet: Spectral Clustering using Deep Neural Networks](https://mlsanity.com/paper/1801.01587/) (2018)
- [Supervised Discrete Hashing](https://mlsanity.com/paper/1503.01557/) (2015)
- [Learning to Hash for Indexing Big Data - A Survey](https://mlsanity.com/paper/1509.05472/) (2015)
- [Stochastic Generative Hashing](https://mlsanity.com/paper/1701.02815/) (2017)
- [BinGAN: Learning Compact Binary Descriptors with a Regularized GAN](https://mlsanity.com/paper/1806.06778/) (2018)
- [Sparse Coding and Autoencoders](https://mlsanity.com/paper/1708.03735/) (2017)
- [Hashing with binary autoencoders](https://mlsanity.com/paper/1501.00756/) (2015)
- [Fast Supervised Discrete Hashing](https://mlsanity.com/paper/1904.03556/) (2019)
- [A Quantized Johnson Lindenstrauss Lemma: The Finding of Buffon's Needle](https://mlsanity.com/paper/1309.1507/) (2013)
- [Ordinal Constrained Binary Code Learning for Nearest Neighbor Search](https://mlsanity.com/paper/1611.06362/) (2016)

## Abstract (arXiv)

Unsupervised hashing has received extensive research focus on the past decade, which typically aims at preserving a predefined metric (i.e. Euclidean metric) in the Hamming space. To this end, the encoding functions of the existing hashing are typically quasi-isometric, which devote to reducing the quantization loss from the target metric space to the discrete Hamming space. However, it is indeed problematic to directly minimize such error, since such mentioned two metric spaces are heterogeneous, and the quasi-isometric mapping is non-linear. The former leads to inconsistent feature distributions, while the latter leads to problematic optimization issues. In this paper, we propose a novel unsupervised hashing method, termed Sparsity-Induced Generative Adversarial Hashing (SiGAH), to encode large-scale high-dimensional features into binary codes, which well solves the two problems through a generative adversarial training framework. Instead of minimizing the quantization loss, our key innovation lies in enforcing the learned Hamming space to have similar data distribution to the target metric space via a generative model. In particular, we formulate a ReLU-based neural network as a generator to output binary codes and an MSE-loss based auto-encoder network as a discriminator, upon which a generative adversarial learning is carried out to train hash functions. Furthermore, to generate the synthetic features from the hash codes, a compressed sensing procedure is introduced into the generative model, which enforces the reconstruction boundary of binary codes to be consistent with that of original features. Finally, such generative adversarial framework can be trained via the Adam optimizer. Experimental results on four benchmarks, i.e., Tiny100K, GIST1M, Deep1M, and MNIST, have shown that the proposed SiGAH has superior performance over the state-of-the-art approaches.