Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning

03/04/2021
by   Hui Wang, et al.
0

Unsupervised domain adaptation (UDA) typically carries out knowledge transfer from a label-rich source domain to an unlabeled target domain by adversarial learning. In principle, existing UDA approaches mainly focus on the global distribution alignment between domains while ignoring the intrinsic local distribution properties. Motivated by this observation, we propose an end-to-end structure-conditioned adversarial learning scheme (SCAL) that is able to preserve the intra-class compactness during domain distribution alignment. By using local structures as structure-aware conditions, the proposed scheme is implemented in a structure-conditioned adversarial learning pipeline. The above learning procedure is iteratively performed by alternating between local structures establishment and structure-conditioned adversarial learning. Experimental results demonstrate the effectiveness of the proposed scheme in UDA scenarios.

READ FULL TEXT

page 1

page 6

research
04/12/2018

Simple Domain Adaptation with Class Prediction Uncertainty Alignment

Unsupervised domain adaptation tries to adapt a classifier trained on a ...
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
10/31/2019

Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning

Joint extraction of aspects and sentiments can be effectively formulated...
research
12/26/2021

FRuDA: Framework for Distributed Adversarial Domain Adaptation

Breakthroughs in unsupervised domain adaptation (uDA) can help in adapti...
research
02/03/2023

Crucial Semantic Classifier-based Adversarial Learning for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA), which aims to explore the transfer...
research
07/14/2020

Spectrum-Guided Adversarial Disparity Learning

It has been a significant challenge to portray intraclass disparity prec...
research
10/10/2018

Domain Confusion with Self Ensembling for Unsupervised Adaptation

Data collection and annotation are time-consuming in machine learning, e...

Please sign up or login with your details

Forgot password? Click here to reset