https://scholars.lib.ntu.edu.tw/handle/123456789/632088
標題: | Adversarial Teacher-Student Representation Learning for Domain Generalization | 作者: | Yang F.-E Cheng Y.-C Shiau Z.-Y YU-CHIANG WANG |
公開日期: | 2021 | 卷: | 23 | 起(迄)頁: | 19448-19460 | 來源出版物: | Advances in Neural Information Processing Systems | 摘要: | Domain generalization (DG) aims to transfer the learning task from a single or multiple source domains to unseen target domains. To extract and leverage the information which exhibits sufficient generalization ability, we propose a simple yet effective approach of Adversarial Teacher-Student Representation Learning, with the goal of deriving the domain generalizable representations via generating and exploring out-of-source data distributions. Our proposed framework advances Teacher-Student learning in an adversarial learning manner, which alternates between knowledge-distillation based representation learning and novel-domain data augmentation. The former progressively updates the teacher network for deriving domain-generalizable representations, while the latter synthesizes data out-ofsource yet plausible distributions. Extensive image classification experiments on benchmark datasets in multiple and single source DG settings confirm that, our model exhibits sufficient generalization ability and performs favorably against state-of-the-art DG methods. © 2021 Neural information processing systems foundation. All rights reserved. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85123340354&partnerID=40&md5=14322725d2943ed80f2dc74df91a4095 https://scholars.lib.ntu.edu.tw/handle/123456789/632088 |
ISSN: | 10495258 | SDG/關鍵字: | Classification (of information); Distillation; Effective approaches; Generalisation; Generalization ability; Learning tasks; Multiple source; Simple++; Single source; Source data; Target domain; Teachers'; Students |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。