IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptation

10/24/2022
by   Shima Rashidi, et al.
0

Distribution shift between train (source) and test (target) datasets is a common problem encountered in machine learning applications. One approach to resolve this issue is to use the Unsupervised Domain Adaptation (UDA) technique that carries out knowledge transfer from a label-rich source domain to an unlabeled target domain. Outliers that exist in either source or target datasets can introduce additional challenges when using UDA in practice. In this paper, α-divergence is used as a measure to minimize the discrepancy between the source and target distributions while inheriting robustness, adjustable with a single parameter α, as the prominent feature of this measure. Here, it is shown that the other well-known divergence-based UDA techniques can be derived as special cases of the proposed method. Furthermore, a theoretical upper bound is derived for the loss in the target domain in terms of the source loss and the initial α-divergence between the two domains. The robustness of the proposed method is validated through testing on several benchmarked datasets in open-set and partial UDA setups where extra classes existing in target and source datasets are considered as outliers.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/10/2022

Unsupervised Domain Adaptation for Extra Features in the Target Domain Using Optimal Transport

Domain adaptation aims to transfer knowledge of labeled instances obtain...
research
12/18/2018

TWINs: Two Weighted Inconsistency-reduced Networks for Partial Domain Adaptation

The task of unsupervised domain adaptation is proposed to transfer the k...
research
05/01/2018

Sample-to-Sample Correspondence for Unsupervised Domain Adaptation

The assumption that training and testing samples are generated from the ...
research
09/16/2021

Unsupervised domain adaptation with non-stochastic missing data

We consider unsupervised domain adaptation (UDA) for classification prob...
research
12/06/2018

Disjoint Label Space Transfer Learning with Common Factorised Space

In this paper, a unified approach is presented to transfer learning that...
research
11/19/2018

Unsupervised Domain Adaptation: An Adaptive Feature Norm Approach

Unsupervised domain adaptation aims to mitigate the domain shift when tr...
research
01/22/2020

Partially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift

This paper proposes a novel approach for unsupervised domain adaptation ...

Please sign up or login with your details

Forgot password? Click here to reset