Unsupervised domain adaption dictionary learning for visual recognition
This addresses the problem of domain shift in visual recognition for computer vision applications, but it is incremental as it builds on existing dictionary learning approaches.
The paper tackles cross-domain visual recognition by proposing an unsupervised domain adaptation method that aligns sparse representations between source and target domains, achieving performance on par or better than state-of-the-art methods on standard datasets.
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.