Asymmetric Transfer Hashing with Adaptive Bipartite Graph Learning

TL;DR

This paper introduces an asymmetric transfer hashing framework with adaptive bipartite graph learning to effectively perform cross-domain retrieval by addressing domain and feature gaps, improving retrieval accuracy.

Contribution

It proposes a novel ATH framework that jointly optimizes asymmetric hash functions and bipartite graphs to transfer knowledge across domains while preserving data structure.

Findings

ATH outperforms state-of-the-art hashing methods on multiple benchmarks.

The adaptive bipartite graph effectively bridges feature gaps between domains.

The framework reduces negative transfer by preserving intrinsic data geometry.

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 feature gap with the help of a novel adaptive bipartite graph constructed on cross-domain data. By jointly optimizing asymmetric hash functions and the bipartite graph, not only can knowledge transfer be achieved but information loss caused by feature alignment can also be avoided. Meanwhile, to alleviate negative transfer, the intrinsic geometrical structure of single-domain data is preserved by involving a domain affinity graph. Extensive experiments on both single-domain and cross-domain benchmarks under different GITR subtasks indicate the superiority of our ATH method in comparison with the state-of-the-art hashing methods.