VisDA2017

VisDA2017 is a popular synthetic-to-real domain adaptation benchmark, which consists of 150k synthetic and 55k real images from 12 categories.

Data and Resources

Cite this as

Xingchao Peng, Qinxun Bai, Xide Xia, Zijun Huang, Kate Saenko, Bo Wang (2024). Dataset: VisDA2017. https://doi.org/10.57702/3ghpzsi8

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.1710.06924
Citation
  • https://doi.org/10.48550/arXiv.2205.04066
Author Xingchao Peng
More Authors
Qinxun Bai
Xide Xia
Zijun Huang
Kate Saenko
Bo Wang
Homepage https://github.com/chester256/MCL