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

by   Jie Wang, et al.

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.


page 1

page 2

page 3

page 4


Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation

Conventional unsupervised domain adaptation (UDA) methods need to access...

Diffusion-based Target Sampler for Unsupervised Domain Adaptation

Limited transferability hinders the performance of deep learning models ...

Unsupervised Domain Adaptation with Progressive Adaptation of Subspaces

Unsupervised Domain Adaptation (UDA) aims to classify unlabeled target d...

ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a l...

Guiding Pseudo-labels with Uncertainty Estimation for Test-Time Adaptation

Standard Unsupervised Domain Adaptation (UDA) methods assume the availab...

IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels

Unsupervised domain adaptation(UDA) has been applied to image semantic s...

Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion

Understanding foggy image sequence in the driving scenes is critical for...

Please sign up or login with your details

Forgot password? Click here to reset