Unveiling Class-Labeling Structure for Universal Domain Adaptation

by   Yueming Yin, et al.

As a more practical setting for unsupervised domain adaptation, Universal Domain Adaptation (UDA) is recently introduced, where the target label set is unknown. One of the big challenges in UDA is how to determine the common label set shared by source and target domains, as there is simply no labeling available in the target domain. In this paper, we employ a probabilistic approach for locating the common label set, where each source class may come from the common label set with a probability. In particular, we propose a novel approach for evaluating the probability of each source class from the common label set, where this probability is computed by the prediction margin accumulated over the whole target domain. Then, we propose a simple universal adaptation network (S-UAN) by incorporating the probabilistic structure for the common label set. Finally, we analyse the generalization bound focusing on the common label set and explore the properties on the target risk for UDA. Extensive experiments indicate that S-UAN works well in different UDA settings and outperforms the state-of-the-art methods by large margins.



There are no comments yet.


page 7


Universal Multi-Source Domain Adaptation

Unsupervised domain adaptation enables intelligent models to transfer kn...

A Sample Selection Approach for Universal Domain Adaptation

We study the problem of unsupervised domain adaption in the universal sc...

On Universal Black-Box Domain Adaptation

In this paper, we study an arguably least restrictive setting of domain ...

Disjoint Label Space Transfer Learning with Common Factorised Space

In this paper, a unified approach is presented to transfer learning that...

Importance Weight Estimation and Generalization in Domain Adaptation under Label Shift

We study generalization under label shift in domain adaptation where the...

Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks

Popular deep domain adaptation methods have mainly focused on learning d...

Generalized Domain Adaptation

Many variants of unsupervised domain adaptation (UDA) problems have been...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.