AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation

TL;DR

AdaMatch is a versatile semi-supervised learning method that unifies domain adaptation tasks, achieving state-of-the-art accuracy across various vision classification benchmarks with minimal hyper-parameter tuning.

Contribution

It introduces AdaMatch, a unified approach that effectively handles SSL, UDA, and SSDA tasks, outperforming existing methods without dataset-specific tuning.

Findings

AdaMatch nearly doubles UDA accuracy on DomainNet.

AdaMatch exceeds prior state-of-the-art with from-scratch training.

Adding a few labeled examples boosts target accuracy significantly.

Abstract

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%.