Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation

TL;DR

This paper introduces a curriculum-based pseudo-labeling method for unsupervised domain adaptation that uses density-based clustering to progressively improve pseudo-label accuracy and feature discriminability, achieving state-of-the-art results.

Contribution

It proposes a novel density-based curriculum for pseudo-labeling and a clustering constraint to enhance feature discriminability in unsupervised domain adaptation.

Findings

Achieves state-of-the-art performance on Office-31, imageCLEF-DA, and Office-Home benchmarks.

Effectively reduces false pseudo-labels by leveraging density-based sample selection.

Improves target feature discriminability through a clustering constraint.

Abstract

To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influence on learning target representations, remains a major challenge. To overcome this issue, we propose a pseudo-labeling curriculum based on a density-based clustering algorithm. Since samples with high density values are more likely to have correct pseudo-labels, we leverage these subsets to train our target network at the early stage, and utilize data subsets with low density values at the later stage. We can progressively improve the capability of our network to generate pseudo-labels, and thus these target samples with pseudo-labels are effective for training our model. Moreover, we present a clustering constraint to enhance the discriminative power of the learned target features. Our approach achieves state-of-the-art performance on three benchmarks: Office-31, imageCLEF-DA, and Office-Home.