Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives

2022/08/15 by Xiaofeng Liu, Liu, Xiaofeng, Chaehwa Yoo +11 · 14 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2208.07422

openalex publication_date 2022/08/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications. However, its success usually relies on two assumptions: (i) vast troves of labeled datasets are required for accurate model fitting, and (ii) training and testing data are independent and identically distributed. Its performance on unseen target domains, thus, is not guaranteed, especially when encountering out-of-distribution data at the adaptation stage. The performance drop on data in a target domain is a critical problem in deploying deep neural networks that are successfully trained on data in a source domain. Unsupervised domain adaptation (UDA) is proposed to counter this, by leveraging both labeled source domain data and unlabeled target domain data to carry out various tasks in the target domain. UDA has yielded promising results on natural image processing, video analysis, natural language processing, time-series data analysis, medical image analysis, etc. In this review, as a rapidly evolving topic, we provide a systematic comparison of its methods and applications. In addition, the connection of UDA with its closely related tasks, e.g., domain generalization and out-of-distribution detection, has also been discussed. Furthermore, deficiencies in current methods and possible promising directions are highlighted.

Cited by

• Domain Adaptation in Structural Health Monitoring of Civil Infrastructure: A Systematic Review
• Neural Collapse in Test-Time Adaptation
• From Simulations to Surveys: Domain Adaptation for Galaxy Observations
• TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation
• Machine and Deep Learning for Indoor UWB Jammer Localization
• A Domain Adaptive Position Reconstruction Method for Time Projection Chamber based on Deep Neural Network
• Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation
• Deep Domain Adaptation for Turbofan Engine Remaining Useful Life Prediction: Methodologies, Evaluation and Future Trends
• Online Adaptation via Dual-Stage Alignment and Self-Supervision for Fast-Calibration Brain-Computer Interfaces
• Grad-CL: Source Free Domain Adaptation with Gradient Guided Feature Disalignment
• Deep Learning for Crack Detection: A Review of Learning Paradigms, Generalizability, and Datasets
• Bridging Simulation and Experiment: A Self-Supervised Domain Adaptation Framework for Concrete Damage Classification
• Semi-Supervised Deep Domain Adaptation for Predicting Solar Power Across Different Locations
• The Geometry of Cortical Computation: Manifold Disentanglement and Predictive Dynamics in VCNet

Related

• A Survey of Unsupervised Deep Domain Adaptation
• Test-time Unsupervised Domain Adaptation
• Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld
• A Survey of Unsupervised Domain Adaptation for Visual Recognition
• Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives