1 code implementation • 7 Dec 2023 • Thomas Westfechtel, Dexuan Zhang, Tatsuya Harada
In a first step, we generate the zero-shot predictions of the source and target dataset using the vision-language model.
Ranked #1 on Domain Adaptation on Office-Home
1 code implementation • 16 Nov 2023 • Thomas Westfechtel, Hao-Wei Yeh, Dexuan Zhang, Tatsuya Harada
Unsupervised domain adaptation (UDA) tries to overcome the need for a large labeled dataset by transferring knowledge from a source dataset, with lots of labeled data, to a target dataset, that has no labeled data.
Ranked #5 on Domain Adaptation on Office-31
no code implementations • 1 Jan 2021 • Dexuan Zhang, Tatsuya Harada
In this paper, we argue that the joint error is essential for the domain adaptation problem, in particular if the samples from different classes in source/target are closely aligned when matching the marginal distributions.
no code implementations • 3 Oct 2019 • Dexuan Zhang, Tatsuya Harada
In this work, we present a novel upper bound of target error to address the problem for unsupervised domain adaptation.