2020

Improve Unsupervised Domain Adaptation with Mixup Training

Yan, Shen, Song, Huan, Li, Nanxiang et al.

Understand

Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain.

Recent work observe that the popular adversarial approach of learning domain-invariant features is insufficient to achieve desirable target domain performance and thus introduce additional training constraints, e.g.
cluster assumption.
However, these approaches impose the constraints on source and target domains individually, ignoring the important interplay between them.

Built on

“Cycada: Cycle-consistent adversarial domain adaptation,”
Judy Hoffman, Eric Tzeng, Taesung Park, Jun-Yan Zhu, Phillip Isola, Kate Saenko, Alexei Efros, and Trevor Darrell, · 2003
Earlier work this paper cites.
“A theory of learning from different domains,”
Shai Ben-David, John Blitzer, Koby Crammer, Alex Kulesza, Fernando Pereira, and Jennifer Wortman Vaughan, · 2010
Earlier work this paper cites.
“Learning transferable features with deep adaptation networks,”
Original
Mingsheng Long, Yue Cao, Jianmin Wang, and Michael I Jordan, · 2015
Earlier work this paper cites.
“Domain-adversarial training of neural networks,”
Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor Lempitsky, · 2016
Earlier work this paper cites.
“Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition,”
Francisco Ordóñez and Daniel Roggen, · 2016
Earlier work this paper cites.
“Deep reconstruction-classification networks for unsupervised domain adaptation,”
Original
Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi, and Wen Li, · 2016
Earlier work this paper cites.

Similar

“Adversarial discriminative domain adaptation,”
Eric Tzeng, Judy Hoffman, Kate Saenko, and Trevor Darrell, · 2017
Cited alongside, same era.
“mixup: Beyond empirical risk minimization,”
Original
Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz, · 2017
Cited alongside, same era.
“A survey on behavior recognition using wifi channel state information,”
Siamak Yousefi, Hirokazu Narui, Sankalp Dayal, Stefano Ermon, and Shahrokh Valaee, · 2017
Cited alongside, same era.
“Asymmetric tri-training for unsupervised domain adaptation,”
Kuniaki Saito, Yoshitaka Ushiku, and Tatsuya Harada, · 2017
Cited alongside, same era.
“Self-ensembling for visual domain adaptation,”
Michelle Fisher Geoffrey French, Michal Mackiewicz, · 2017
Cited alongside, same era.
“Personal sensing: understanding mental health using ubiquitous sensors and machine learning,”
David C Mohr, Mi Zhang, and Stephen M Schueller, · 2017
Cited alongside, same era.

Then

“Conditional adversarial domain adaptation,”
Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Michael I Jordan, · 2018
Later among the works it cites.
“A dirt-t approach to unsupervised domain adaptation,”
Rui Shu, Hung H Bui, Hirokazu Narui, and Stefano Ermon, · 2018
Later among the works it cites.
“Virtual adversarial training: a regularization method for supervised and semi-supervised learning,”
Takeru Miyato, Shin-ichi Maeda, Masanori Koyama, and Shin Ishii, · 2018
Later among the works it cites.
“Optimizing kernel machines using deep learning,”
Huan Song, Jayaraman J Thiagarajan, Prasanna Sattigeri, and Andreas Spanias, · 2018
Later among the works it cites.
“Joint domain alignment and discriminative feature learning for unsupervised deep domain adaptation,”
Chao Chen, Zhihong Chen, Boyuan Jiang, and Xinyu Jin, · 2019
Later among the works it cites.
“Mixmatch: A holistic approach to semi-supervised learning,”
Original
David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, and Colin Raffel, · 2019
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…