Deep Discrete Hashing with Self-supervised Pairwise Labels

TL;DR

This paper introduces an unsupervised deep hashing method called Deep Discrete Hashing (DDH) that directly learns binary codes for large-scale image retrieval and classification, outperforming existing methods.

Contribution

The paper proposes a novel unsupervised deep hashing framework that effectively learns discrete binary codes without labels, using neighborhood structure-based loss functions.

Findings

DDH significantly outperforms existing hashing methods in mAP for image retrieval.

DDH achieves superior accuracy in object recognition tasks.

Experimental results on CIFAR-10, NUS-WIDE, and Oxford-17 validate its effectiveness.

Abstract

Hashing methods have been widely used for applications of large-scale image retrieval and classification. Non-deep hashing methods using handcrafted features have been significantly outperformed by deep hashing methods due to their better feature representation and end-to-end learning framework. However, the most striking successes in deep hashing have mostly involved discriminative models, which require labels. In this paper, we propose a novel unsupervised deep hashing method, named Deep Discrete Hashing (DDH), for large-scale image retrieval and classification. In the proposed framework, we address two main problems: 1) how to directly learn discrete binary codes? 2) how to equip the binary representation with the ability of accurate image retrieval and classification in an unsupervised way? We resolve these problems by introducing an intermediate variable and a loss function steering the learning process, which is based on the neighborhood structure in the original space. Experimental results on standard datasets (CIFAR-10, NUS-WIDE, and Oxford-17) demonstrate that our DDH significantly outperforms existing hashing methods by large margin in terms of~mAP for image retrieval and object recognition. Code is available at \url{https://github.com/htconquer/ddh}.