A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

• Published in: IEEE transaction on neural networks and learning systems Vol. 33; no. 2; pp. 473 - 493
• Main Authors: Zhao, Sicheng, Yue, Xiangyu, Zhang, Shanghang, Li, Bo, Zhao, Han, Wu, Bichen, Krishna, Ravi, Gonzalez, Joseph E., Sangiovanni-Vincentelli, Alberto L., Seshia, Sanjit A., Keutzer, Kurt
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Adaptation models; Adaptation, Physiological; Adversarial learning; Artificial neural networks; Benchmarking; Benchmarks; Data models; Datasets; discrepancy-based methods; domain adaptation (DA); Domains; Learning algorithms; Learning systems; Loss measurement; Machine Learning; Neural networks; Neural Networks, Computer; self-supervised learning (SSL); Task analysis; Training; transfer learning; Visual tasks; Visualization
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2020.3028503

Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. However, in many applications, it is prohibitively expensive and time-consuming to obtain large quantities of labeled data. To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain. Unfortunately, direct transfer across domains often performs poorly due to the presence of domain shift or dataset bias . Domain adaptation (DA) is a machine learning paradigm that aims to learn a model from a source domain that can perform well on a different (but related) target domain. In this article, we review the latest single-source deep unsupervised DA methods focused on visual tasks and discuss new perspectives for future research. We begin with the definitions of different DA strategies and the descriptions of existing benchmark datasets. We then summarize and compare different categories of single-source unsupervised DA methods, including discrepancy-based methods, adversarial discriminative methods, adversarial generative methods, and self-supervision-based methods. Finally, we discuss future research directions with challenges and possible solutions.