Cycle-consistent Conditional Adversarial Transfer Networks

09/17/2019
by   Jingjing Li, et al.
0

Domain adaptation investigates the problem of cross-domain knowledge transfer where the labeled source domain and unlabeled target domain have distinctive data distributions. Recently, adversarial training have been successfully applied to domain adaptation and achieved state-of-the-art performance. However, there is still a fatal weakness existing in current adversarial models which is raised from the equilibrium challenge of adversarial training. Specifically, although most of existing methods are able to confuse the domain discriminator, they cannot guarantee that the source domain and target domain are sufficiently similar. In this paper, we propose a novel approach named cycle-consistent conditional adversarial transfer networks (3CATN) to handle this issue. Our approach takes care of the domain alignment by leveraging adversarial training. Specifically, we condition the adversarial networks with the cross-covariance of learned features and classifier predictions to capture the multimodal structures of data distributions. However, since the classifier predictions are not certainty information, a strong condition with the predictions is risky when the predictions are not accurate. We, therefore, further propose that the truly domain-invariant features should be able to be translated from one domain to the other. To this end, we introduce two feature translation losses and one cycle-consistent loss into the conditional adversarial domain adaptation networks. Extensive experiments on both classical and large-scale datasets verify that our model is able to outperform previous state-of-the-arts with significant improvements.

READ FULL TEXT
research
04/09/2019

Domain-Symmetric Networks for Adversarial Domain Adaptation

Unsupervised domain adaptation aims to learn a model of classifier for u...
research
04/27/2020

Maximum Density Divergence for Domain Adaptation

Unsupervised domain adaptation addresses the problem of transferring kno...
research
02/23/2018

A DIRT-T Approach to Unsupervised Domain Adaptation

Domain adaptation refers to the problem of leveraging labeled data in a ...
research
03/30/2020

Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training

Domain adaptation tackles the problem of transferring knowledge from a l...
research
11/06/2020

Domain adaptation techniques for improved cross-domain study of galaxy mergers

In astronomy, neural networks are often trained on simulated data with t...
research
08/25/2021

CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training

How to generate conditional synthetic data for a domain without utilizin...
research
12/15/2018

Domain-to-Domain Translation Model for Recommender System

Recently multi-domain recommender systems have received much attention f...

Please sign up or login with your details

Forgot password? Click here to reset