CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算
Towards Corruption-Agnostic Robust Domain Adaptation
Xu, Yifan1,2; Sheng, Kekai3; Dong, Weiming1,4; Wu, Baoyuan5; Xu, Changsheng1,2; Hu, Bao-Gang1
Source PublicationACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
ISSN1551-6857
2022-11-01
Volume18Issue:4Pages:16
Abstract

Great progress has been achieved in domain adaptation in decades. Existing works are always based on an ideal assumption that testing target domains are independent and identically distributed with training target domains. However, due to unpredictable corruptions (e.g., noise and blur) in real data, such as web images and real-world object detection, domain adaptation methods are increasingly required to be corruption robust on target domains. We investigate a new task, corruption-agnostic robust domain adaptation (CRDA), to be accurate on original data and robust against unavailable-for-training corruptions on target domains. This task is non-trivial due to the large domain discrepancy and unsupervised target domains. We observe that simple combinations of popular methods of domain adaptation and corruption robustness have suboptimal CRDA results. We propose a newapproach based on two technical insights into CRDA, as follows: (1) an easy-to-plug module called domain discrepancy generator (DDG) that generates samples that enlarge domain discrepancy to mimic unpredictable corruptions; (2) a simple but effective teacher-student scheme with contrastive loss to enhance the constraints on target domains. Experiments verify that DDG maintains or even improves its performance on original data and achieves better corruption robustness than baselines. Our code is available at: https://github.com/YifanXu74/CRDA.

KeywordDomain adaptation corruption robustness transfer learning
DOI10.1145/3501800
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[U20B2070] ; National Natural Science Foundation of China[61832016] ; National Natural Science Foundation of China[62036012] ; National Natural Science Foundation of China[61720106006] ; CASIA-Tencent Youtu joint research project
Funding OrganizationNational Natural Science Foundation of China ; CASIA-Tencent Youtu joint research project
WOS Research AreaComputer Science
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS IDWOS:000776441600010
PublisherASSOC COMPUTING MACHINERY
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48205
Collection模式识别国家重点实验室_多媒体计算
Corresponding AuthorDong, Weiming
Affiliation1.Chinese Acad Sci, NLPR, Inst Automat, 95 East Zhongguancun Rd, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, 95 East Zhongguancun Rd, Beijing 100190, Peoples R China
3.Tencent Inc, Youtu Lab, 397 Tianlin Rd, Shanghai 201103, Peoples R China
4.CASIA LLvis Joint Lab, 95 East Zhongguancun Rd, Beijing 100190, Peoples R China
5.Chinese Univ Hong Kong, Shenzhen Res Inst Big Data, 2001 Longxiang Rd, Shenzhen 518172, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China;  Institute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Xu, Yifan,Sheng, Kekai,Dong, Weiming,et al. Towards Corruption-Agnostic Robust Domain Adaptation[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2022,18(4):16.
APA Xu, Yifan,Sheng, Kekai,Dong, Weiming,Wu, Baoyuan,Xu, Changsheng,&Hu, Bao-Gang.(2022).Towards Corruption-Agnostic Robust Domain Adaptation.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,18(4),16.
MLA Xu, Yifan,et al."Towards Corruption-Agnostic Robust Domain Adaptation".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 18.4(2022):16.
Files in This Item:
File Name/Size DocType Version Access License
3501800.pdf(2116KB)期刊论文作者接受稿开放获取CC BY-NC-SAView
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xu, Yifan]'s Articles
[Sheng, Kekai]'s Articles
[Dong, Weiming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xu, Yifan]'s Articles
[Sheng, Kekai]'s Articles
[Dong, Weiming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xu, Yifan]'s Articles
[Sheng, Kekai]'s Articles
[Dong, Weiming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 3501800.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.