no code implementations • 26 Feb 2024 • Hanbing Liu, Jingge Wang, Xuan Zhang, Ye Guo, Yang Li
Specifically, we construct a transfer curriculum over the source and intermediate domains based on Wasserstein distance, motivated by theoretical analysis of CDA.
no code implementations • 11 Jul 2022 • Jingge Wang, Liyan Xie, Yao Xie, Shao-Lun Huang, Yang Li
Domain generalization aims at learning a universal model that performs well on unseen target domains, incorporating knowledge from multiple source domains.
no code implementations • 8 Sep 2021 • Jingge Wang, Yang Li, Liyan Xie, Yao Xie
Given multiple source domains, domain generalization aims at learning a universal model that performs well on any unseen but related target domain.