Sparse-inductive Generative Adversarial Hashing For Nearest Neighbor Search

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2023sparse

Related papers

• Deep Semantic Hashing With Generative Adversarial Networks (2018)13.50
• Learning To Hash With Semantic Similarity Metrics And Empirical KL Divergence (2020)0.00
• Beyond Neighbourhood-preserving Transformations For Quantization-based Unsupervised Hashing (2021)4.52
• Self-supervised Bernoulli Autoencoders For Semi-supervised Hashing (2020)3.66
• NASH: Toward End-to-end Neural Architecture For Generative Semantic Hashing (2018)10.07
• Experimental Analysis Of Locality Sensitive Hashing Techniques For High-dimensional Approximate Nearest Neighbor Searches (2020)6.34
• A Survey On Learning To Hash (2016)21.62
• On The Adversarial Robustness Of Locality-sensitive Hashing In Hamming Space (2024)2.26