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

by   Xiaofeng Liu, et al.

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.


A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

Large-scale labeled training datasets have enabled deep neural networks ...

Neural Unsupervised Domain Adaptation in NLP—A Survey

Deep neural networks excel at learning from labeled data and achieve sta...

Source-Free Unsupervised Domain Adaptation: A Survey

Unsupervised domain adaptation (UDA) via deep learning has attracted app...

A New Bidirectional Unsupervised Domain Adaptation Segmentation Framework

Domain shift happens in cross-domain scenarios commonly because of the w...

Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey

Video analysis tasks such as action recognition have received increasing...

Multi-scale Feature Alignment for Continual Learning of Unlabeled Domains

Methods for unsupervised domain adaptation (UDA) help to improve the per...

Remaining Useful Lifetime Prediction via Deep Domain Adaptation

In Prognostics and Health Management (PHM) sufficient prior observed deg...

Please sign up or login with your details

Forgot password? Click here to reset