Unsupervised domain adaption dictionary learning for visual recognition

TL;DR

This paper introduces an unsupervised domain adaptation method using dictionary learning to improve cross-domain visual recognition, aligning data distributions by enforcing similar sparse representations across source and target domains.

Contribution

It proposes a novel approach that jointly learns dictionaries for source and target domains, aligning their data distributions without requiring labeled data in the target domain.

Findings

Performs on par or better than state-of-the-art methods

Effective in aligning source and target data distributions

Applicable to standard visual recognition datasets

Abstract

Over the last years, dictionary learning method has been extensively applied to deal with various computer vision recognition applications, and produced state-of-the-art results. However, when the data instances of a target domain have a different distribution than that of a source domain, the dictionary learning method may fail to perform well. In this paper, we address the cross-domain visual recognition problem and propose a simple but effective unsupervised domain adaption approach, where labeled data are only from source domain. In order to bring the original data in source and target domain into the same distribution, the proposed method forcing nearest coupled data between source and target domain to have identical sparse representations while jointly learning dictionaries for each domain, where the learned dictionaries can reconstruct original data in source and target domain respectively. So that sparse representations of original data can be used to perform visual recognition tasks. We demonstrate the effectiveness of our approach on standard datasets. Our method performs on par or better than competitive state-of-the-art methods.