Spotlight Poster

Semi-Supervised Domain Generalization with Known and Unknown Classes

Lei Zhang · Ji-Fu Li · Wei Wang

Great Hall & Hall B1+B2 (level 1) #1023
[ ]
[ Paper [ Poster [ OpenReview
Tue 12 Dec 8:45 a.m. PST — 10:45 a.m. PST

Abstract:

Semi-Supervised Domain Generalization (SSDG) aims to learn a model that is generalizable to an unseen target domain with only a few labels, and most existing SSDG methods assume that unlabeled training and testing samples are all known classes. However, a more realistic scenario is that known classes may be mixed with some unknown classes in unlabeled training and testing data. To deal with such a scenario, we propose the Class-Wise Adaptive Exploration and Exploitation (CWAEE) method. In particular, we explore unlabeled training data by using one-vs-rest classifiers and class-wise adaptive thresholds to detect known and unknown classes, and exploit them by adopting consistency regularization on augmented samples based on Fourier Transformation to improve the unseen domain generalization. The experiments conducted on real-world datasets verify the effectiveness and superiority of our method.

Chat is not available.