paper-with-me

UDE-DomainNet

홈페이지 · 논문 1편

Different from the setting of domain adaptation which uses all labeled source and unlabeled target domain examples for training, domain examples should be divided into two disjoint parts: training and test. UDE-DomainNet is built from DomainNet, so the performance of domain-adapted or domain-expanded models on the source and target domain can be evaluated.

벤치마크

Unsupervised Domain Expansion on UDE-DomainNet 결과 1개