Unsupervised Domain Adaptation Based Image Synthesis and Synergistic Adversarial Learning for Optic Disc and Cup Segmentation

2021 ◽  
Author(s):  
Weixin Liu ◽  
Haijun Lei ◽  
Hai Xie ◽  
Benjian Zhao ◽  
Baiying Lei
Keyword(s):  
Optic Disc ◽  
Domain Adaptation ◽  
Image Synthesis ◽  
Adversarial Learning ◽  
Unsupervised Domain Adaptation

Unsupervised domain adaptation with adversarial learning for mass detection in mammogram

2020 ◽  
Vol 393 ◽  
pp. 27-37 ◽  
Author(s):  
Rongbo Shen ◽  
Jianhua Yao ◽  
Kezhou Yan ◽  
Kuan Tian ◽  
Cheng Jiang ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Mass Detection ◽  
Adversarial Learning ◽  
Unsupervised Domain Adaptation

scholarly journals Unsupervised Domain Adaptation on Reading Comprehension

2020 ◽  
Vol 34 (05) ◽  
pp. 7480-7487
Author(s):  
Yu Cao ◽  
Meng Fang ◽  
Baosheng Yu ◽  
Joey Tianyi Zhou
Keyword(s):  
Reading Comprehension ◽  
Large Scale ◽  
Domain Adaptation ◽  
Generalization Capability ◽  
Target Domain ◽  
Adversarial Learning ◽  
Unsupervised Domain Adaptation ◽  
Comparable Performance ◽  
Benchmark Datasets ◽  
Contextual Representation

Reading comprehension (RC) has been studied in a variety of datasets with the boosted performance brought by deep neural networks. However, the generalization capability of these models across different domains remains unclear. To alleviate the problem, we investigate unsupervised domain adaptation on RC, wherein a model is trained on the labeled source domain and to be applied to the target domain with only unlabeled samples. We first show that even with the powerful BERT contextual representation, a model can not generalize well from one domain to another. To solve this, we provide a novel conditional adversarial self-training method (CASe). Specifically, our approach leverages a BERT model fine-tuned on the source dataset along with the confidence filtering to generate reliable pseudo-labeled samples in the target domain for self-training. On the other hand, it further reduces domain distribution discrepancy through conditional adversarial learning across domains. Extensive experiments show our approach achieves comparable performance to supervised models on multiple large-scale benchmark datasets.

Sign in / Sign up

Export Citation Format

Share Document