Deep asymmetric hashing with dual semantic regression and class structure quantization

DOI10.1016/J.INS.2021.12.112MaRDI QIDQ6125443zbMATH OpenOpenAlexFDO

Authors Jianglin Lü, Hailing Wang, Jie Zhou, Mengfan Yan, Jiajun Wen

Publication date 11 April 2024

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2110.12478

zbMATH Keywords

asymmetric hashingclass structure quantizationdual semantic regression

Mathematics Subject Classification ID

Computer science (68-XX) Information and communication theory, circuits (94-XX)

Abstract: Recently, deep hashing methods have been widely used in image retrieval task. Most existing deep hashing approaches adopt one-to-one quantization to reduce information loss. However, such class-unrelated quantization cannot give discriminative feedback for network training. In addition, these methods only utilize single label to integrate supervision information of data for hashing function learning, which may result in inferior network generalization performance and relatively low-quality hash codes since the inter-class information of data is totally ignored. In this paper, we propose a dual semantic asymmetric hashing (DSAH) method, which generates discriminative hash codes under three-fold constraints. Firstly, DSAH utilizes class prior to conduct class structure quantization so as to transmit class information during the quantization process. Secondly, a simple yet effective label mechanism is designed to characterize both the intra-class compactness and inter-class separability of data, thereby achieving semantic-sensitive binary code learning. Finally, a meaningful pairwise similarity preserving loss is devised to minimize the distances between class-related network outputs based on an affinity graph. With these three main components, high-quality hash codes can be generated through network. Extensive experiments conducted on various datasets demonstrate the superiority of DSAH in comparison with state-of-the-art deep hashing methods.

Cites work

• A general framework for deep supervised discrete hashing
• Deep Discrete Supervised Hashing
• Discrete Spectral Hashing for Efficient Similarity Retrieval
• GLDH: toward more efficient global low-density locality-sensitive hashing for high dimensions
• Locality-sensitive hashing scheme based on p-stable distributions
• Sparse graph based self-supervised hashing for scalable image retrieval
• Visualizing data using t-SNE

This page was built for publication: Deep asymmetric hashing with dual semantic regression and class structure quantization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6125443)