DeepAI AI Chat
Log In Sign Up

NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing

by   Dinghan Shen, et al.
Duke University

Semantic hashing has become a powerful paradigm for fast similarity search in many information retrieval systems. While fairly successful, previous techniques generally require two-stage training, and the binary constraints are handled ad-hoc. In this paper, we present an end-to-end Neural Architecture for Semantic Hashing (NASH), where the binary hashing codes are treated as Bernoulli latent variables. A neural variational inference framework is proposed for training, where gradients are directly back-propagated through the discrete latent variable to optimize the hash function. We also draw connections between proposed method and rate-distortion theory, which provides a theoretical foundation for the effectiveness of the proposed framework. Experimental results on three public datasets demonstrate that our method significantly outperforms several state-of-the-art models on both unsupervised and supervised scenarios.


page 1

page 2

page 3

page 4


Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator

Semantic hashing has become a crucial component of fast similarity searc...

Unsupervised Multi-Index Semantic Hashing

Semantic hashing represents documents as compact binary vectors (hash co...

Scalable Gaussian Processes for Supervised Hashing

We propose a flexible procedure for large-scale image search by hash fun...

Unsupervised Hashing with Contrastive Information Bottleneck

Many unsupervised hashing methods are implicitly established on the idea...

Deep Hashing with Category Mask for Fast Video Retrieval

This paper proposes an end-to-end deep hashing framework with category m...

Convolutional Hashing for Automated Scene Matching

We present a powerful new loss function and training scheme for learning...

Document Hashing with Mixture-Prior Generative Models

Hashing is promising for large-scale information retrieval tasks thanks ...