Semi-Supervised Domain Adaptation via Selective Pseudo Labeling and Progressive Self-Training

Domain adaptation (DA) is a representation learning methodology that transfers knowledge from a label-sufficient source domain to a label-scarce target domain. While most of early methods are focused on unsupervised DA (UDA), several studies on semi-supervised DA (SSDA) are recently suggested. In SS...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Kim, Yoonhyung, Kim, Changick
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 01.04.2021
Subjects
Adaptation
Domains
Knowledge management
Labels
Learning
Target recognition
Training
Online AccessGet full text

Cover

More Information
Summary:Domain adaptation (DA) is a representation learning methodology that transfers knowledge from a label-sufficient source domain to a label-scarce target domain. While most of early methods are focused on unsupervised DA (UDA), several studies on semi-supervised DA (SSDA) are recently suggested. In SSDA, a small number of labeled target images are given for training, and the effectiveness of those data is demonstrated by the previous studies. However, the previous SSDA approaches solely adopt those data for embedding ordinary supervised losses, overlooking the potential usefulness of the few yet informative clues. Based on this observation, in this paper, we propose a novel method that further exploits the labeled target images for SSDA. Specifically, we utilize labeled target images to selectively generate pseudo labels for unlabeled target images. In addition, based on the observation that pseudo labels are inevitably noisy, we apply a label noise-robust learning scheme, which progressively updates the network and the set of pseudo labels by turns. Extensive experimental results show that our proposed method outperforms other previous state-of-the-art SSDA methods.
ISSN:2331-8422