Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners
This work addresses the challenge of domain adaptation for researchers and practitioners by revealing a close relationship between UDA and SSL, potentially improving model performance with fewer annotations.
The paper tackles the problem of reducing manual annotations in machine learning by showing that semi-supervised learning (SSL) methods can be effectively applied to unsupervised domain adaptation (UDA) tasks, with state-of-the-art SSL methods significantly outperforming existing UDA methods on the DomainNet benchmark.
Unsupervised domain adaptation (UDA) and semi-supervised learning (SSL) are two typical strategies to reduce expensive manual annotations in machine learning. In order to learn effective models for a target task, UDA utilizes the available labeled source data, which may have different distributions from unlabeled samples in the target domain, while SSL employs few manually annotated target samples. Although UDA and SSL are seemingly very different strategies, we find that they are closely related in terms of task objectives and solutions, and SSL is a special case of UDA problems. Based on this finding, we further investigate whether SSL methods work on UDA tasks. By adapting eight representative SSL algorithms on UDA benchmarks, we show that SSL methods are strong UDA learners. Especially, state-of-the-art SSL methods significantly outperform existing UDA methods on the challenging UDA benchmark of DomainNet, and state-of-the-art UDA methods could be further enhanced with SSL techniques. We thus promote that SSL methods should be employed as baselines in future UDA studies and expect that the revealed relationship between UDA and SSL could shed light on future UDA development. Codes are available at \url{https://github.com/YBZh}.