Towards Corruption-Agnostic Robust Domain Adaptation
Xu, Yifan1,2; Sheng, Kekai3; Dong, Weiming1,4; Wu, Baoyuan5; Xu, Changsheng1,2; Hu, Bao-Gang1
发表期刊ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
ISSN1551-6857
2022-11-01
卷号18期号:4页码:16
摘要

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.

关键词Domain adaptation corruption robustness transfer learning
DOI10.1145/3501800
收录类别SCI
语种英语
资助项目National 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
项目资助者National Natural Science Foundation of China ; CASIA-Tencent Youtu joint research project
WOS研究方向Computer Science
WOS类目Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号WOS:000776441600010
出版者ASSOC COMPUTING MACHINERY
七大方向——子方向分类机器学习
引用统计
被引频次:3[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/48205
专题多模态人工智能系统全国重点实验室_多媒体计算
通讯作者Dong, Weiming
作者单位1.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
第一作者单位模式识别国家重点实验室
通讯作者单位模式识别国家重点实验室;  中国科学院自动化研究所
推荐引用方式
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.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
3501800.pdf(2116KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Xu, Yifan]的文章
[Sheng, Kekai]的文章
[Dong, Weiming]的文章
百度学术
百度学术中相似的文章
[Xu, Yifan]的文章
[Sheng, Kekai]的文章
[Dong, Weiming]的文章
必应学术
必应学术中相似的文章
[Xu, Yifan]的文章
[Sheng, Kekai]的文章
[Dong, Weiming]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 3501800.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。