Asymmetric Transfer Hashing With Adaptive Bipartite Graph Learning

Abstract

Thanks to the efficient retrieval speed and low storage consumption, learning to hash has been widely used in visual retrieval tasks. However, existing hashing methods assume that the query and retrieval samples lie in homogeneous feature space within the same domain. As a result, they cannot be directly applied to heterogeneous cross-domain retrieval. In this paper, we propose a Generalized Image Transfer Retrieval (GITR) problem, which encounters two crucial bottlenecks: 1) the query and retrieval samples may come from different domains, leading to an inevitable \{domain distribution gap\}; 2) the features of the two domains may be heterogeneous or misaligned, bringing up an additional \{feature gap\}. To address the GITR problem, we propose an Asymmetric Transfer Hashing (ATH) framework with its unsupervised/semi-supervised/supervised realizations. Specifically, ATH characterizes the domain distribution gap by the discrepancy between two asymmetric hash functions, and minimizes the

Stats

• citations14
• S2 citations—
• github stars0
• HF likes0
• heat score8.82
• arxiv keylu2022asymmetric

Related papers

• Transfer Adversarial Hashing For Hamming Space Retrieval (2017)8.60
• One Network For Multi-domains: Domain Adaptive Hashing With Intersectant Generative Adversarial Network (2019)7.81
• Deep Self-adaptive Hashing For Image Retrieval (2021)8.35
• Exploring Auxiliary Context: Discrete Semantic Transfer Hashing For Scalable Image Retrieval (2019)15.88
• Transitive Hashing Network For Heterogeneous Multimedia Retrieval (2016)8.35
• Attributes Grouping And Mining Hashing For Fine-grained Image Retrieval (2023)10.07
• Task-adaptive Asymmetric Deep Cross-modal Hashing (2020)9.41
• SSDH: Semi-supervised Deep Hashing For Large Scale Image Retrieval (2016)15.40