1 code implementation • 23 Jun 2022 • Shogo Sagawa, Hideitsu Hino
In previous work, it is assumed that the number of intermediate domains is large and the distance between adjacent domains is small; hence, the gradual domain adaptation algorithm, involving self-training with unlabeled datasets, is applicable.
1 code implementation • 9 Feb 2022 • Shogo Sagawa, Hideitsu Hino
Practically, the cost of samples in intermediate domains will vary, and it is natural to consider that the closer an intermediate domain is to the target domain, the higher the cost of obtaining samples from the intermediate domain is.