Deep Supervised Discrete Hashing

TL;DR

This paper introduces a deep supervised discrete hashing method that directly learns binary codes optimized for classification, leveraging pairwise labels and classification info, outperforming existing methods.

Contribution

It proposes a novel deep hashing algorithm that directly constrains outputs to binary codes and integrates pairwise and classification information in a unified framework.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively exploits semantic information for improved retrieval.

Uses an alternating minimization approach for discrete optimization.

Abstract

With the rapid growth of image and video data on the web, hashing has been extensively studied for image or video search in recent years. Benefit from recent advances in deep learning, deep hashing methods have achieved promising results for image retrieval. However, there are some limitations of previous deep hashing methods (e.g., the semantic information is not fully exploited). In this paper, we develop a deep supervised discrete hashing algorithm based on the assumption that the learned binary codes should be ideal for classification. Both the pairwise label information and the classification information are used to learn the hash codes within one stream framework. We constrain the outputs of the last layer to be binary codes directly, which is rarely investigated in deep hashing algorithm. Because of the discrete nature of hash codes, an alternating minimization method is used to optimize the objective function. Experimental results have shown that our method outperforms current state-of-the-art methods on benchmark datasets.