Improving Pseudo Labels With Intra-Class Similarity for Unsupervised Domain Adaptation

TL;DR

This paper introduces a novel method to enhance pseudo labels in unsupervised domain adaptation by exploiting intra-class similarities, leading to improved domain transfer performance.

Contribution

It proposes an iterative pseudo label refinement technique using intra-class similarity and spanning trees, improving accuracy over conventional UDA methods.

Findings

Enhanced pseudo label accuracy improves target domain feature discrimination.

The method boosts performance of several baseline UDA algorithms.

Results show more domain-invariant features after applying the approach.

Abstract

Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a different but related fully-unlabeled target domain. To address the problem of domain shift, more and more UDA methods adopt pseudo labels of the target samples to improve the generalization ability on the target domain. However, inaccurate pseudo labels of the target samples may yield suboptimal performance with error accumulation during the optimization process. Moreover, once the pseudo labels are generated, how to remedy the generated pseudo labels is far from explored. In this paper, we propose a novel approach to improve the accuracy of the pseudo labels in the target domain. It first generates coarse pseudo labels by a conventional UDA method. Then, it iteratively exploits the intra-class similarity of the target samples for improving the generated coarse pseudo labels, and aligns the source and target domains with the improved pseudo labels. The accuracy improvement of the pseudo labels is made by first deleting dissimilar samples, and then using spanning trees to eliminate the samples with the wrong pseudo labels in the intra-class samples. We have applied the proposed approach to several conventional UDA methods as an additional term. Experimental results demonstrate that the proposed method can boost the accuracy of the pseudo labels and further lead to more discriminative and domain invariant features than the conventional baselines.