Simulations of Common Unsupervised Domain Adaptation Algorithms for Image Classification

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.

Accepted in IEEE TIM

References in corpus (12)

• mixup: Beyond Empirical Risk Minimization
• The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions
• ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases
• Deep Domain Confusion: Maximizing for Domain Invariance
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Deep Subdomain Adaptation Network for Image Classification
• VisDA: The Visual Domain Adaptation Challenge
• Maximum Density Divergence for Domain Adaptation
• MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs
• CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
• Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation
• Out-of-Distribution Representation Learning for Time Series Classification

Cited by in corpus (2)

• Domain Adaptation Techniques for Natural and Medical Image Classification
• Enhancing Dual Network Based Semi-Supervised Medical Image Segmentation with Uncertainty-Guided Pseudo-Labeling