Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation

09/11/2020
by   Jinghua Wang, et al.
9

Machine learning models trained in one domain perform poorly in the other domains due to the existence of domain shift. Domain adaptation techniques solve this problem by training transferable models from the label-rich source domain to the label-scarce target domain. Unfortunately, a majority of the existing domain adaptation techniques rely on the availability of target-domain data, and thus limit their applications to a small community across few computer vision problems. In this paper, we tackle the challenging zero-shot domain adaptation (ZSDA) problem, where target-domain data is non-available in the training stage. For this purpose, we propose conditional coupled generative adversarial networks (CoCoGAN) by extending the coupled generative adversarial networks (CoGAN) into a conditioning model. Compared with the existing state of the arts, our proposed CoCoGAN is able to capture the joint distribution of dual-domain samples in two different tasks, i.e. the relevant task (RT) and an irrelevant task (IRT). We train CoCoGAN with both source-domain samples in RT and dual-domain samples in IRT to complete the domain adaptation. While the former provide high-level concepts of the non-available target-domain data, the latter carry the sharing correlation between the two domains in RT and IRT. To train CoCoGAN in the absence of target-domain data for RT, we propose a new supervisory signal, i.e. the alignment between representations across tasks. Extensive experiments carried out demonstrate that our proposed CoCoGAN outperforms existing state of the arts in image classifications.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 7

page 8

page 9

research
09/11/2020

Adversarial Learning for Zero-shot Domain Adaptation

Zero-shot domain adaptation (ZSDA) is a category of domain adaptation pr...
research
07/06/2017

Zero-Shot Deep Domain Adaptation

The existing methods of domain adaptation (DA) work under the assumption...
research
05/11/2018

Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks

Existing deep learning methods of video recognition usually require a la...
research
11/24/2017

CatGAN: Coupled Adversarial Transfer for Domain Generation

This paper introduces a Coupled adversarial transfer GAN (CatGAN), an ef...
research
07/14/2023

Unsupervised Domain Adaptation using Lexical Transformations and Label Injection for Twitter Data

Domain adaptation is an important and widely studied problem in natural ...
research
06/24/2016

Coupled Generative Adversarial Networks

We propose coupled generative adversarial network (CoGAN) for learning a...

Please sign up or login with your details

Forgot password? Click here to reset