DeepAI AI Chat
Log In Sign Up

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

05/14/2018
by   Dinghan Shen, et al.
Duke University
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

05/21/2020

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

Semantic hashing has become a crucial component of fast similarity searc...
03/26/2021

Unsupervised Multi-Index Semantic Hashing

Semantic hashing represents documents as compact binary vectors (hash co...
04/25/2016

Scalable Gaussian Processes for Supervised Hashing

We propose a flexible procedure for large-scale image search by hash fun...
05/13/2021

Unsupervised Hashing with Contrastive Information Bottleneck

Many unsupervised hashing methods are implicitly established on the idea...
12/22/2017

Deep Hashing with Category Mask for Fast Video Retrieval

This paper proposes an end-to-end deep hashing framework with category m...
02/09/2018

Convolutional Hashing for Automated Scene Matching

We present a powerful new loss function and training scheme for learning...
08/29/2019

Document Hashing with Mixture-Prior Generative Models

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