Inter-domain curriculum learning for domain generalization

Domain generalization aims to learn a domain-invariant representation from multiple source domains so that a model can generalize well across unseen target domains. Such models are often trained with examples that are presented randomly from all source domains, which can make the training unstable d...

Full description

Bibliographic Details
Main Authors: Daehee Kim, Jinkyu Kim, Jaekoo Lee
Format: Article
Language:English
Published: Elsevier 2022-06-01
Series:ICT Express
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405959521001648