Where and How to Transfer: Knowledge Aggregation-Induced Transferability Perception for Unsupervised Domain Adaptation
文献类型:期刊论文
作者 | Dong JH(董家华)2,3,4![]() ![]() ![]() |
刊名 | IEEE Transactions on Pattern Analysis and Machine Intelligence
![]() |
出版日期 | 2021 |
页码 | 1-17 |
关键词 | Transfer Learning Unsupervised Domain Adaptation Semantic Segmentation Medical Lesions Diagnosis |
ISSN号 | 0162-8828 |
产权排序 | 1 |
英文摘要 | Unsupervised domain adaptation without accessing expensive annotation processes of target data has achieved remarkable successes in semantic segmentation. However, most existing state-of-the-art methods cannot explore whether semantic representations across domains are transferable or not, which may result in the negative transfer brought by irrelevant knowledge. To tackle this challenge, in this paper, we develop a novel Knowledge Aggregation-induced Transferability Perception (KATP) for unsupervised domain adaptation, which is a pioneering attempt to distinguish transferable or untransferable knowledge across domains. Specifically, the KATP module is designed to quantify which semantic knowledge across domains is transferable, by incorporating transferability information propagation from global category-wise prototypes. Based on KATP, we design a novel KATP Adaptation Network (KATPAN) to determine where and how to transfer. The KATPAN contains a transferable appearance translation module T_A() and a transferable representation augmentation module T_R(), where both modules construct a virtuous circle of performance promotion. T_A() develops a transferability-aware information bottleneck to highlight where to adapt transferable visual characterizations and modality information; T_R() explores how to augment transferable representations while abandoning untransferable information, and promotes the translation performance of T_A() in return. Experiments on several representative datasets and a medical dataset support the state-of-the-art performance of our model. |
语种 | 英语 |
资助机构 | National Key Research and Development Program of China under Grant 2019YFB1310300 ; National Nature Science Foundation of China under Grant 61821005, and Grant 62003336 ; National Postdoctoral Innovative Talents Support Program (BX20200353) |
源URL | [http://ir.sia.cn/handle/173321/30084] ![]() |
专题 | 沈阳自动化研究所_机器人学研究室 |
通讯作者 | Cong Y(丛杨) |
作者单位 | 1.Department of Computer Science, Tulane University, New Orleans, LA 70118, USA. 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China 4.University of Chinese Academy of Sciences, Beijing, 100049, China 5.Faculty of Engineering and Information Technology, University of Technology, Sydney, NSW 2007, Australia |
推荐引用方式 GB/T 7714 | Dong JH,Cong Y,Sun G,et al. Where and How to Transfer: Knowledge Aggregation-Induced Transferability Perception for Unsupervised Domain Adaptation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2021:1-17. |
APA | Dong JH,Cong Y,Sun G,Fang, Zhen,&Ding ZM.(2021).Where and How to Transfer: Knowledge Aggregation-Induced Transferability Perception for Unsupervised Domain Adaptation.IEEE Transactions on Pattern Analysis and Machine Intelligence,1-17. |
MLA | Dong JH,et al."Where and How to Transfer: Knowledge Aggregation-Induced Transferability Perception for Unsupervised Domain Adaptation".IEEE Transactions on Pattern Analysis and Machine Intelligence (2021):1-17. |
入库方式: OAI收割
来源:沈阳自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。