Bayesian Uncertainty Matching for Unsupervised Domain Adaptation

06/24/2019
by   Jun Wen, et al.
0

Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reducing domain shift by matching marginal feature distributions through deep transformations on the input features, due to the unavailability of target domain labels. We show that domain shift may still exist via label distribution shift at the classifier, thus deteriorating model performances. To alleviate this issue, we propose an approximate joint distribution matching scheme by exploiting prediction uncertainty. Specifically, we use a Bayesian neural network to quantify prediction uncertainty of a classifier. By imposing distribution matching on both features and labels (via uncertainty), label distribution mismatching in source and target data is effectively alleviated, encouraging the classifier to produce consistent predictions across domains. We also propose a few techniques to improve our method by adaptively reweighting domain adaptation loss to achieve nontrivial distribution matching and stable training. Comparisons with state of the art unsupervised domain adaptation methods on three popular benchmark datasets demonstrate the superiority of our approach, especially on the effectiveness of alleviating negative transfer.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/12/2018

Exploiting Local Feature Patterns for Unsupervised Domain Adaptation

Unsupervised domain adaptation methods aim to alleviate performance degr...
research
07/01/2021

Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation

Understanding unsupervised domain adaptation has been an important task ...
research
02/16/2016

Unsupervised Domain Adaptation Using Approximate Label Matching

Domain adaptation addresses the problem created when training data is ge...
research
03/02/2015

Deep Transfer Network: Unsupervised Domain Adaptation

Domain adaptation aims at training a classifier in one dataset and apply...
research
05/24/2020

Discriminative Active Learning for Domain Adaptation

Domain Adaptation aiming to learn a transferable feature between differe...
research
05/30/2023

ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Models

We study the domain adaptation problem with label shift in this work. Un...
research
03/06/2022

Domain Adaptation with Factorizable Joint Shift

Existing domain adaptation (DA) usually assumes the domain shift comes f...

Please sign up or login with your details

Forgot password? Click here to reset