Deep Asymmetric Hashing With Dual Semantic Regression And Class Structure Quantization

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 o

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keylu2021deep

Related papers

• Dual Asymmetric Deep Hashing Learning (2018)9.03
• Self-supervised Asymmetric Deep Hashing With Margin-scalable Constraint (2020)0.00
• Deep Class-wise Hashing: Semantics-preserving Hashing Via Class-wise Loss (2018)11.19
• Deep Hashing With Semantic Hash Centers For Image Retrieval (2025)2.26
• Dual-level Semantic Transfer Deep Hashing For Efficient Social Image Retrieval (2020)12.33
• Deep Supervised Discrete Hashing (2017)0.00
• Hierarchy Neighborhood Discriminative Hashing For An Unified View Of Single-label And Multi-label Image Retrieval (2019)0.00
• HHF: Hashing-guided Hinge Function For Deep Hashing Retrieval (2021)14.24