14
3

Pick up the PACE: Fast and Simple Domain Adaptation via Ensemble Pseudo-Labeling

Abstract

Domain Adaptation (DA) has received widespread attention from deep learning researchers in recent years because of its potential to improve test accuracy with out-of-distribution labeled data. Most state-of-the-art DA algorithms require an extensive amount of hyperparameter tuning and are computationally intensive due to the large batch sizes required. In this work, we propose a fast and simple DA method consisting of three stages: (1) domain alignment by covariance matching, (2) pseudo-labeling, and (3) ensembling. We call this method PACE\textbf{PACE}, for P\textbf{P}seudo-labels, A\textbf{A}lignment of C\textbf{C}ovariances, and E\textbf{E}nsembles. PACE is trained on top of fixed features extracted from an ensemble of modern pretrained backbones. PACE exceeds previous state-of-the-art by 5 - 10 %\textbf{5 - 10 \%} on most benchmark adaptation tasks without training a neural network. PACE reduces training time and hyperparameter tuning time by 82%82\% and 97%97\%, respectively, when compared to state-of-the-art DA methods. Code is released here: https://github.com/Chris210634/PACE-Domain-Adaptation

View on arXiv
Comments on this paper