CA-UDA: Class-Aware Unsupervised Domain Adaptation with Optimal Assignment and Pseudo-Label Refinement

05/26/2022
by   Can Zhang, et al.
0

Recent works on unsupervised domain adaptation (UDA) focus on the selection of good pseudo-labels as surrogates for the missing labels in the target data. However, source domain bias that deteriorates the pseudo-labels can still exist since the shared network of the source and target domains are typically used for the pseudo-label selections. The suboptimal feature space source-to-target domain alignment can also result in unsatisfactory performance. In this paper, we propose CA-UDA to improve the quality of the pseudo-labels and UDA results with optimal assignment, a pseudo-label refinement strategy and class-aware domain alignment. We use an auxiliary network to mitigate the source domain bias for pseudo-label refinement. Our intuition is that the underlying semantics in the target domain can be fully exploited to help refine the pseudo-labels that are inferred from the source features under domain shift. Furthermore, our optimal assignment can optimally align features in the source-to-target domains and our class-aware domain alignment can simultaneously close the domain gap while preserving the classification decision boundaries. Extensive experiments on several benchmark datasets show that our method can achieve state-of-the-art performance in the image classification task.

READ FULL TEXT

page 1

page 2

page 4

page 5

page 6

page 7

page 8

page 9

research
11/21/2018

Progressive Feature Alignment for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) transfers knowledge from a label-ri...
research
08/04/2020

Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation

Heterogeneous domain adaptation (HDA) transfers knowledge across source ...
research
08/15/2023

Context-Aware Pseudo-Label Refinement for Source-Free Domain Adaptive Fundus Image Segmentation

In the domain adaptation problem, source data may be unavailable to the ...
research
08/16/2022

Subtype-Aware Dynamic Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) has been successfully applied to tr...
research
08/24/2020

Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID

In this technical report, we present our submission to the VisDA Challen...
research
08/21/2020

Graph Neural Networks for UnsupervisedDomain Adaptation of Histopathological ImageAnalytics

Annotating histopathological images is a time-consuming andlabor-intensi...
research
09/01/2020

Unsupervised Domain Adaptation with Progressive Adaptation of Subspaces

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

Please sign up or login with your details

Forgot password? Click here to reset