Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation

被引:67
作者
Sharma, Astuti [1 ]
Kalluri, Tarun [1 ]
Chandraker, Manmohan [1 ]
机构
[1] Univ Calif San Diego, La Jolla, CA 92093 USA
来源
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 | 2021年
关键词
D O I
10.1109/CVPR46437.2021.00532
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Domain adaptation deals with training models using large scale labeled data from a specific source domain and then adapting the knowledge to certain target domains that have few or no labels. Many prior works learn domain agnostic feature representations for this purpose using a global distribution alignment objective which does not take into account the finer class specific structure in the source and target domains. We address this issue in our work and propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA. We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process. ILA-DA simultaneously accounts for intra-class clustering as well as inter-class separation among the categories, resulting in less noisy classifier boundaries, improved transferability and increased accuracy. We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets and provide insights into the proposed alignment approach. Code will be made publicly available at https://github.com/astuti/ILA-DA.
引用
收藏
页码:5357 / 5367
页数:11
相关论文
共 80 条
[1]  
[Anonymous], 2017, P IEEE C COMP VIS PA
[2]  
Arora S, 2019, PR MACH LEARN RES, V97
[3]   Ensemble Deep Manifold Similarity Learning using Hard Proxies [J].
Aziere, Nicolas ;
Todorovic, Sinisa .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :7291-7299
[4]  
Baktashmotlagh M, 2016, J MACH LEARN RES, V17
[5]   A theory of learning from different domains [J].
Ben-David, Shai ;
Blitzer, John ;
Crammer, Koby ;
Kulesza, Alex ;
Pereira, Fernando ;
Vaughan, Jennifer Wortman .
MACHINE LEARNING, 2010, 79 (1-2) :151-175
[6]  
Ben-David Shai, 2006, Advances in Neural Information Processing Systems (NeurIPS), V19
[7]  
Bousmalis K., 2016, P INT C NEUR INF PRO, P343
[8]   Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks [J].
Bousmalis, Konstantinos ;
Silberman, Nathan ;
Dohan, David ;
Erhan, Dumitru ;
Krishnan, Dilip .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :95-104
[9]   Domain Adaptation Problems: A DASVM Classification Technique and a Circular Validation Strategy [J].
Bruzzone, Lorenzo ;
Marconcini, Mattia .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (05) :770-787
[10]   Progressive Feature Alignment for Unsupervised Domain Adaptation [J].
Chen, Chaoqi ;
Xie, Weiping ;
Huang, Wenbing ;
Rong, Yu ;
Ding, Xinghao ;
Huang, Yue ;
Xu, Tingyang ;
Huang, Junzhou .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :627-636