Simulations of Common Unsupervised Domain Adaptation Algorithms for Image Classification

TL;DR

This paper evaluates recent unsupervised domain adaptation algorithms for image classification through simulations, comparing their performance across datasets and discussing their strengths, limitations, and future research directions.

Contribution

It provides a comprehensive simulation-based comparison of recent UDA techniques, highlighting their performance variations and practical challenges.

Findings

SSRT achieved 91.6% accuracy on office-31 dataset

Performance drops observed with limited batch sizes in Office-Home

The study identifies key challenges and future directions in UDA research

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 data sets. Domain adaptation (DA) is a machine learning technique that aims to address this problem by reducing the differences between domains. This paper presents simulation-based algorithms of recent DA techniques, mainly related to unsupervised domain adaptation (UDA), where labels are available only in the source domain. Our study compares these techniques with public data sets 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 data set during our simulations, however, the accuracy dropped to 72.4\% in the Office-Home data set 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.