Abstract:
Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applic...Show MoreMetadata
Abstract:
Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance drops when the trained model is used in new datasets. Domain adaptation (DA) is a machine learning technique that aims to address this problem by reducing the differences between domains. This article presents simulation-based algorithms of recent DA techniques, mainly related to unsupervised DA (UDA), where labels are available only in the source domain. Our study compares these techniques with public datasets and diverse characteristics, highlighting their respective strengths and drawbacks. For example, safe self-refinement for transformer-based DA (SSRT) achieved the highest accuracy (91.6%) in the office-31 dataset during our simulations, however, the accuracy dropped to 72.4% in the Office-Home dataset when using limited batch sizes. In addition to improving the reader’s comprehension of recent techniques in DA, our study also highlights challenges and upcoming directions for research in this domain. The codes are available at https://github.com/AIPMLab/Domain_Adaptation.
Published in: IEEE Transactions on Instrumentation and Measurement ( Volume: 74)