2 code implementations • 18 Nov 2019 • Toshihiko Matsuura, Tatsuya Harada
Conventional methods assume that the domain to which each sample belongs is known in training.
Ranked #72 on Domain Generalization on PACS
no code implementations • 18 Dec 2018 • Toshihiko Matsuura, Kuniaki Saito, Tatsuya Harada
We utilize two classification networks to estimate the ratio of the target samples in each class with which a classification loss is weighted to adapt the classes present in the target domain.