Supervised Hashing with End-to-End Binary Deep Neural Network

TL;DR

This paper introduces an end-to-end deep neural network for supervised image hashing that directly learns binary codes, preserving similarity and balancing properties, and outperforms existing methods on large-scale datasets.

Contribution

It presents a novel deep architecture and learning scheme for supervised hashing that effectively handles binary constraints and improves retrieval performance.

Findings

Outperforms state-of-the-art hashing methods on multiple benchmarks

Scalable to large datasets due to efficient learning scheme

Maintains similarity, independence, and balance in binary codes

Abstract

Image hashing is a popular technique applied to large scale content-based visual retrieval due to its compact and efficient binary codes. Our work proposes a new end-to-end deep network architecture for supervised hashing which directly learns binary codes from input images and maintains good properties over binary codes such as similarity preservation, independence, and balancing. Furthermore, we also propose a new learning scheme that can cope with the binary constrained loss function. The proposed algorithm not only is scalable for learning over large-scale datasets but also outperforms state-of-the-art supervised hashing methods, which are illustrated throughout extensive experiments from various image retrieval benchmarks.