AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation
This addresses the challenge of training models on one data distribution and testing on another for vision classification, with broad applicability across tasks, though it is incremental in unifying existing approaches.
The paper tackles the problem of domain adaptation by introducing AdaMatch, a unified method for unsupervised domain adaptation, semi-supervised learning, and semi-supervised domain adaptation, which nearly doubles accuracy on DomainNet and exceeds prior state-of-the-art by 6.4% when trained from scratch.
We extend semi-supervised learning to the problem of domain adaptation to learn significantly higher-accuracy models that train on one data distribution and test on a different one. With the goal of generality, we introduce AdaMatch, a method that unifies the tasks of unsupervised domain adaptation (UDA), semi-supervised learning (SSL), and semi-supervised domain adaptation (SSDA). In an extensive experimental study, we compare its behavior with respective state-of-the-art techniques from SSL, SSDA, and UDA on vision classification tasks. We find AdaMatch either matches or significantly exceeds the state-of-the-art in each case using the same hyper-parameters regardless of the dataset or task. For example, AdaMatch nearly doubles the accuracy compared to that of the prior state-of-the-art on the UDA task for DomainNet and even exceeds the accuracy of the prior state-of-the-art obtained with pre-training by 6.4% when AdaMatch is trained completely from scratch. Furthermore, by providing AdaMatch with just one labeled example per class from the target domain (i.e., the SSDA setting), we increase the target accuracy by an additional 6.1%, and with 5 labeled examples, by 13.6%.