Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment

10/13/2021
by   Yin Zhao, et al.
0

Eliminating the covariate shift cross domains is one of the common methods to deal with the issue of domain shift in visual unsupervised domain adaptation. However, current alignment methods, especially the prototype based or sample-level based methods neglect the structural properties of the underlying distribution and even break the condition of covariate shift. To relieve the limitations and conflicts, we introduce a novel concept named (virtual) mirror, which represents the equivalent sample in another domain. The equivalent sample pairs, named mirror pairs reflect the natural correspondence of the empirical distributions. Then a mirror loss, which aligns the mirror pairs cross domains, is constructed to enhance the alignment of the domains. The proposed method does not distort the internal structure of the underlying distribution. We also provide theoretical proof that the mirror samples and mirror loss have better asymptotic properties in reducing the domain shift. By applying the virtual mirror and mirror loss to the generic unsupervised domain adaptation model, we achieved consistent superior performance on several mainstream benchmarks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/23/2019

Generalized Domain Adaptation with Covariate and Label Shift CO-ALignment

Unsupervised knowledge transfer has a great potential to improve the gen...
research
09/17/2022

Mitigating Both Covariate and Conditional Shift for Domain Generalization

Domain generalization (DG) aims to learn a model on several source domai...
research
05/16/2017

Joint Geometrical and Statistical Alignment for Visual Domain Adaptation

This paper presents a novel unsupervised domain adaptation method for cr...
research
06/23/2020

Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment

In this study, we focus on the unsupervised domain adaptation problem wh...
research
06/23/2020

Discriminative Feature Alignment: ImprovingTransferability of Unsupervised DomainAdaptation by Gaussian-guided LatentAlignment

In this study, we focus on the unsupervised domain adaptation problem wh...
research
06/09/2020

Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation

We present an approach for unsupervised domain adaptation—with a strong ...
research
06/07/2022

Searching for Optimal Subword Tokenization in Cross-domain NER

Input distribution shift is one of the vital problems in unsupervised do...

Please sign up or login with your details

Forgot password? Click here to reset