Single domain generalization via unsupervised diversity probe

Single domain generalization (SDG) is a realistic yet challenging domain generalization scenario that aims to generalize a model trained on a single domain to multiple unseen domains. Typical SDG methods are essentially supervised data augmentation strategies, which tend to enhance the novelty rathe...

Full description

Bibliographic Details

Main Authors:	Kehua Guo, Rui Ding, Tian Qiu, Xiangyuan Zhu, Zheng Wu, Liwei Wang, Hui Fang
Format:	Default Conference proceeding
Published:	2023
Subjects:	single domain generalization adversarial data augmentation unsupervised learning mutual information
Online Access:	https://hdl.handle.net/2134/23845314.v1
Tags:	Add Tag No Tags, Be the first to tag this record!