Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation

2020 ◽  
pp. 1-1 ◽  
Author(s):  
Weichen Zhang ◽  
Dong Xu ◽  
Wanli Ouyang ◽  
Wen Li
Keyword(s):  
Domain Adaptation ◽  
Unsupervised Domain Adaptation ◽  
Adversarial Network

Importance-weighted conditional adversarial network for unsupervised domain adaptation

2020 ◽  
Vol 155 ◽  
pp. 113404 ◽  
Author(s):  
Peng Liu ◽  
Ting Xiao ◽  
Cangning Fan ◽  
Wei Zhao ◽  
Xianglong Tang ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Unsupervised Domain Adaptation ◽  
Adversarial Network

Hybrid adversarial network for unsupervised domain adaptation

2020 ◽  
Vol 514 ◽  
pp. 44-55 ◽  
Author(s):  
Changchun Zhang ◽  
Qingjie Zhao ◽  
Yu Wang
Keyword(s):  
Domain Adaptation ◽  
Unsupervised Domain Adaptation ◽  
Adversarial Network

scholarly journals Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation

2020 ◽  
Author(s):  
Yiyang Zhang ◽  
Feng Liu ◽  
Zhen Fang ◽  
Bo Yuan ◽  
Guangquan Zhang ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Unlabeled Data ◽  
Target Domain ◽  
Source Domain ◽  
Label Data ◽  
Unsupervised Domain Adaptation ◽  
Adversarial Network ◽  
True Label ◽  
Source Data ◽  
One Step

In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain. However, it may be difficult to collect fully-true-label data in a source domain given limited budget. To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA). The key benefit is that it is much less costly to collect complementary-label source data (required by BFUDA) than collecting the true-label source data (required by ordinary UDA). To this end, complementary label adversarial network (CLARINET) is proposed to solve the BFUDA problem. CLARINET maintains two deep networks simultaneously, where one focuses on classifying complementary-label source data and the other takes care of the source-to-target distributional adaptation. Experiments show that CLARINET significantly outperforms a series of competent baselines.

scholarly journals Unsupervised Domain Adaptation for Facial Expression Recognition Using Generative Adversarial Networks

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Xiaoqing Wang ◽  
Xiangjun Wang ◽  
Yubo Ni
Keyword(s):  
Facial Expression ◽  
Facial Expression Recognition ◽  
Domain Adaptation ◽  
Recognition Task ◽  
Fine Tuning ◽  
Generative Adversarial Networks ◽  
Expression Recognition ◽  
Generative Adversarial Network ◽  
Unsupervised Domain Adaptation ◽  
Adversarial Network

In the facial expression recognition task, a good-performing convolutional neural network (CNN) model trained on one dataset (source dataset) usually performs poorly on another dataset (target dataset). This is because the feature distribution of the same emotion varies in different datasets. To improve the cross-dataset accuracy of the CNN model, we introduce an unsupervised domain adaptation method, which is especially suitable for unlabelled small target dataset. In order to solve the problem of lack of samples from the target dataset, we train a generative adversarial network (GAN) on the target dataset and use the GAN generated samples to fine-tune the model pretrained on the source dataset. In the process of fine-tuning, we give the unlabelled GAN generated samples distributed pseudolabels dynamically according to the current prediction probabilities. Our method can be easily applied to any existing convolutional neural networks (CNN). We demonstrate the effectiveness of our method on four facial expression recognition datasets with two CNN structures and obtain inspiring results.

Sign in / Sign up

Export Citation Format

Share Document