Unsupervised Domain Adaptation using Regularized Hyper-graph Matching

TL;DR

This paper introduces an unsupervised domain adaptation method that uses hyper-graph matching with class regularization to align source and target data distributions, improving image classification across domains.

Contribution

It presents a novel hyper-graph matching approach with class regularization and an efficient optimization algorithm for unsupervised domain adaptation.

Findings

Outperforms state-of-the-art methods on standard datasets

Effective in aligning source and target domain distributions

Computationally efficient due to sample selection and optimized routines

Abstract

Domain adaptation (DA) addresses the real-world image classification problem of discrepancy between training (source) and testing (target) data distributions. We propose an unsupervised DA method that considers the presence of only unlabelled data in the target domain. Our approach centers on finding matches between samples of the source and target domains. The matches are obtained by treating the source and target domains as hyper-graphs and carrying out a class-regularized hyper-graph matching using first-, second- and third-order similarities between the graphs. We have also developed a computationally efficient algorithm by initially selecting a subset of the samples to construct a graph and then developing a customized optimization routine for graph-matching based on Conditional Gradient and Alternating Direction Multiplier Method. This allows the proposed method to be used widely. We also performed a set of experiments on standard object recognition datasets to validate the effectiveness of our framework over state-of-the-art approaches.