Open Compound Domain Adaptation

被引:73
作者
Liu, Ziwei [1 ]
Miao, Zhongqi [2 ]
Pan, Xingang [1 ]
Zhan, Xiaohang [1 ]
Lin, Dahua [1 ]
Yu, Stella X. [2 ]
Gong, Boqing [3 ]
机构
[1] Chinese Univ Hong Kong, Hong Kong, Peoples R China
[2] Univ Calif Berkeley, ICSI, Berkeley, CA 94704 USA
[3] Google Inc, Seattle, WA USA
来源
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020) | 2020年
关键词
D O I
10.1109/CVPR42600.2020.01242
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A typical domain adaptation approach is to adapt models trained on the annotated data in a source domain (e.g., sunny weather) for achieving high performance on the test data in a target domain (e.g., rainy weather). Whether the target contains a single homogeneous domain or multiple heterogeneous domains, existing works always assume that there exist clear distinctions between the domains, which is often not true in practice (e.g., changes in weather). We study an open compound domain adaptation (OCDA) problem, in which the target is a compound of multiple homogeneous domains without domain labels, reflecting realistic data collection from mixed and novel situations. We propose a new approach based on two technical insights into OCDA: 1) a curriculum domain adaptation strategy to bootstrap generalization across domains in a data-driven self-organizing fashion and 2) a memory module to increase the model's agility towards novel domains. Our experiments on digit classification, facial expression recognition, semantic segmentation, and reinforcement learning demonstrate the effectiveness of our approach.
引用
收藏
页码:12403 / 12412
页数:10
相关论文
共 56 条
[1]  
Ajakan H., 2016, Journal of Machine Learning Research, V17, P2096, DOI 10.48550/arXiv.1505.07818
[2]  
[Anonymous], 2018, ICML
[3]  
[Anonymous], 2017, CVPR
[4]  
[Anonymous], 2017, CVPR, DOI DOI 10.1109/CVPR.2017.684
[5]  
[Anonymous], 2014, AAAI
[6]  
[Anonymous], 2017, ICML
[7]  
Bobu A., 2018, PROC ICLR WORKSHOP, P1
[8]   Open Set Domain Adaptation [J].
Busto, Pau Panareda ;
Gall, Juergen .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :754-763
[9]   Partial Adversarial Domain Adaptation [J].
Cao, Zhangjie ;
Ma, Lijia ;
Long, Mingsheng ;
Wang, Jianmin .
COMPUTER VISION - ECCV 2018, PT VIII, 2018, 11212 :139-155
[10]   Inhibitory Effect of 7-Demethoxytylophorine on Penicillium italicum and its Possible Mechanism [J].
Chen, Chuying ;
Qi, Wenwen ;
Peng, Xuan ;
Chen, Jinyin ;
Wan, Chunpeng .
MICROORGANISMS, 2019, 7 (02)