Data Augmentation with norm-VAE and Selective Pseudo-Labelling for Unsupervised Domain Adaptation

Wang, Q.; Meng, F.; Breckon, T.P.

Abstract

We address the Unsupervised Domain Adaptation (UDA) problem in image classification from a new perspective. In contrast to most existing works which either align the data distributions or learn domain-invariant features, we directly learn a unified classifier for both the source and target domains in the high-dimensional homogeneous feature space without explicit domain alignment. To this end, we employ the effective Selective Pseudo-Labelling (SPL) technique to take advantage of the unlabelled samples in the target domain. Surprisingly, data distribution discrepancy across the source and target domains can be well handled by a computationally simple classifier (e.g., a shallow Multi-Layer Perceptron) trained in the original feature space. Besides, we propose a novel generative model norm-AE to generate synthetic features for the target domain as a data augmentation strategy to enhance the classifier training. Experimental results on several benchmark datasets demonstrate the pseudo-labelling strategy itself can lead to comparable performance to many state-of-the-art methods whilst the use of norm-AE for feature augmentation can further improve the performance in most cases. As a result, our proposed methods (i.e. naiveSPL and norm-AE-SPL) can achieve comparable performance with state-of-the-art methods with the average accuracy of 93.4% and 90.4% on Office-Caltech and ImageCLEF-DA datasets, and achieve competitive performance on Digits, Office31 and Office-Home datasets with the average accuracy of 97.2%, 87.6% and 68.6% respectively.

Citation

Wang, Q., Meng, F., & Breckon, T. (2023). Data Augmentation with norm-VAE and Selective Pseudo-Labelling for Unsupervised Domain Adaptation. Neural Networks, 161, 614-625. https://doi.org/10.1016/j.neunet.2023.02.006

• Journal Article Type: Article
• Acceptance Date: Feb 5, 2023
• Online Publication Date: Feb 22, 2023
• Publication Date: 2023-02
• Deposit Date: Feb 7, 2023
• Publicly Available Date: Feb 24, 2023
• Journal: Neural Networks
• Print ISSN: 0893-6080
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 161
• Pages: 614-625
• DOI: https://doi.org/10.1016/j.neunet.2023.02.006
• Public URL: https://durham-repository.worktribe.com/output/1181396