• DOI:10.1109/ICCV.2019.00149
Corpus ID: 54458071

Moment Matching for Multi-Source Domain Adaptation

@article{Peng2019MomentMF,
  title={Moment Matching for Multi-Source Domain Adaptation},
  author={Xingchao Peng and Qinxun Bai and Xide Xia and Zijun Huang and Kate Saenko and Bo Wang},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={1406-1415}
}

Xingchao Peng, Qinxun Bai, +3 authors Bo Wang

Published 2019

Computer Science

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are collected from multiple sources, requiring multi-source domain adaptation. We make three major contributions towards addressing this problem. First, we collect and annotate by far the largest UDA dataset, called DomainNet, which contains six domains and about 0.6 million images distributed among 345 categories… CONTINUE READING

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed