Better pseudo-label: Joint domain-aware label and dual-classifier for semi-supervised domain generalization

作者：

Highlights：

• The method is designed for the semi-supervised domain generalization problem.

• The method predicts accurate pseudo-labels under domain shift via domain-aware pseudo-labeling and dual-classifier structure.

• The method leverages both confident and ambiguous unlabeled samples to improve generalization.

摘要

•The method is designed for the semi-supervised domain generalization problem.•The method predicts accurate pseudo-labels under domain shift via domain-aware pseudo-labeling and dual-classifier structure.•The method leverages both confident and ambiguous unlabeled samples to improve generalization.

论文关键词：Semi-supervised learning,Domain generalization,Image recognition,Feature representation

论文评审过程：Received 7 November 2021, Revised 4 August 2022, Accepted 16 August 2022, Available online 18 August 2022, Version of Record 29 August 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108987