Exploiting Local Feature Patterns for Unsupervised Domain Adaptation

11/12/2018
by   Jun Wen, et al.
0

Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local features and their multi-mode statistics. We show that the learned local feature patterns are more generic and transferable and a further local feature distribution matching enables fine-grained feature alignment. In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics. Comparisons to the state-of-the-art unsupervised domain adaptation methods on two popular benchmark datasets demonstrate the superiority of our approach and its effectiveness on alleviating negative transfer.

READ FULL TEXT

page 3

page 5

research
06/24/2019

Bayesian Uncertainty Matching for Unsupervised Domain Adaptation

Domain adaptation is an important technique to alleviate performance deg...
research
03/07/2019

Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss

A classifier trained on a dataset seldom works on other datasets obtaine...
research
08/03/2020

Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition

Data inconsistency and bias are inevitable among different facial expres...
research
03/16/2019

Domain adaptation for holistic skin detection

Human skin detection in images is a widely studied topic of Computer Vis...
research
03/10/2021

Limitations of Post-Hoc Feature Alignment for Robustness

Feature alignment is an approach to improving robustness to distribution...
research
03/25/2021

MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation

For unsupervised domain adaptation (UDA), to alleviate the effect of dom...
research
12/06/2016

Correlation Alignment for Unsupervised Domain Adaptation

In this chapter, we present CORrelation ALignment (CORAL), a simple yet ...

Please sign up or login with your details

Forgot password? Click here to reset