Preserving Semantic Consistency in Unsupervised Domain Adaptation Using Generative Adversarial Networks

04/28/2021
by   Mohammad Mahfujur Rahman, et al.
0

Unsupervised domain adaptation seeks to mitigate the distribution discrepancy between source and target domains, given labeled samples of the source domain and unlabeled samples of the target domain. Generative adversarial networks (GANs) have demonstrated significant improvement in domain adaptation by producing images which are domain specific for training. However, most of the existing GAN based techniques for unsupervised domain adaptation do not consider semantic information during domain matching, hence these methods degrade the performance when the source and target domain data are semantically different. In this paper, we propose an end-to-end novel semantic consistent generative adversarial network (SCGAN). This network can achieve source to target domain matching by capturing semantic information at the feature level and producing images for unsupervised domain adaptation from both the source and the target domains. We demonstrate the robustness of our proposed method which exceeds the state-of-the-art performance in unsupervised domain adaptation settings by performing experiments on digit and object classification tasks.

READ FULL TEXT
research
06/04/2018

Factorized Adversarial Networks for Unsupervised Domain Adaptation

In this paper, we propose Factorized Adversarial Networks (FAN) to solve...
research
02/27/2022

Attention-based Cross-Layer Domain Alignment for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) aims to learn transferable knowledg...
research
12/10/2019

Learning Domain Adaptive Features with Unlabeled Domain Bridges

Conventional cross-domain image-to-image translation or unsupervised dom...
research
09/03/2023

Spectral Adversarial MixUp for Few-Shot Unsupervised Domain Adaptation

Domain shift is a common problem in clinical applications, where the tra...
research
09/10/2018

Improving Adversarial Discriminative Domain Adaptation

Adversarial discriminative domain adaptation (ADDA) is an efficient fram...
research
01/03/2020

Improve Unsupervised Domain Adaptation with Mixup Training

Unsupervised domain adaptation studies the problem of utilizing a releva...
research
12/16/2016

Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks

Collecting well-annotated image datasets to train modern machine learnin...

Please sign up or login with your details

Forgot password? Click here to reset