Efficient Pre-trained Features and Recurrent Pseudo-Labeling in Unsupervised Domain Adaptation

TL;DR

This paper introduces an efficient method for unsupervised domain adaptation by selecting optimal pre-trained features from multiple ImageNet models and employing a recurrent pseudo-labeling approach, significantly improving accuracy and reducing computation time.

Contribution

It proposes a novel approach combining the selection of best pre-trained features with a recurrent pseudo-labeling model for unsupervised domain adaptation.

Findings

Achieves high accuracy on benchmark datasets

Reduces computation time compared to existing methods

Outperforms state-of-the-art in unsupervised domain adaptation

Abstract

Domain adaptation (DA) mitigates the domain shift problem when transferring knowledge from one annotated domain to another similar but different unlabeled domain. However, existing models often utilize one of the ImageNet models as the backbone without exploring others, and fine-tuning or retraining the backbone ImageNet model is also time-consuming. Moreover, pseudo-labeling has been used to improve the performance in the target domain, while how to generate confident pseudo labels and explicitly align domain distributions has not been well addressed. In this paper, we show how to efficiently opt for the best pre-trained features from seventeen well-known ImageNet models in unsupervised DA problems. In addition, we propose a recurrent pseudo-labeling model using the best pre-trained features (termed PRPL) to improve classification performance. To show the effectiveness of PRPL, we evaluate it on three benchmark datasets, Office+Caltech-10, Office-31, and Office-Home. Extensive experiments show that our model reduces computation time and boosts the mean accuracy to 98.1%, 92.4%, and 81.2%, respectively, substantially outperforming the state of the art.