Data augmentation has been observed playing a crucial role in achieving better generalization in many machine learning tasks, especially in unsupervised domain adaptation (DA). It is particularly effective on visual object recognition tasks as images are high-dimensional with an enormous range of variations that can be simulated. Existing data augmentation techniques, however, are not explicitly designed to address the differences between different domains. Expert knowledge about the data is required, as well as manual efforts in finding the optimal parameters. In this article, we propose a novel domain-adaptive augmentation method by making use of a state-of-the-art style transfer method and domain discrepancy measurement. Specifically, we measure the discrepancy between source and target domains, and use it as a guide to augment the original source samples using style transferred source-to-target samples. The proposed domain-adaptive augmentation method is data and model agnostic that can be easily incorporated with state-of-the-art DA algorithms. We show empirically that, by using this domain-adaptive augmentation, we are able to gradually reduce the discrepancy between the source and target samples, and further boost the adaptation performance using different DA algorithms on three popular domain adaption datasets.
|Number of pages||12|
|Journal||IEEE Transactions on Neural Networks and Learning Systems|
|Early online date||07 Dec 2021|
|Publication status||Early online date - 07 Dec 2021|
FingerprintDive into the research topics of 'Discrepancy-Guided Domain-Adaptive Data Augmentation'. Together they form a unique fingerprint.
Unsupervised visual domain adaptation by self-guided learningAuthor: Gao, J., Dec 2022
Supervisor: Hua, Y. (Supervisor) & Wang, H. (Supervisor)
Student thesis: Doctoral Thesis › Doctor of PhilosophyFile