OpenCompoundDomainAdaptation OCDA Save

Pytorch implementation for "Open Compound Domain Adaptation" (CVPR 2020 ORAL)

Project README

Open Compound Domain Adaptation

[Project] [Paper] [Demo] [Blog]


Open Compound Domain Adaptation (OCDA) is the author's re-implementation of the compound domain adaptator described in:
"Open Compound Domain Adaptation"
Ziwei Liu*Zhongqi Miao*Xingang PanXiaohang ZhanDahua LinStella X. YuBoqing Gong  (CUHK & Berkeley & Google)  in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020, Oral Presentation

Further information please contact Zhongqi Miao and Ziwei Liu.



  • 11/09/2020: We have uploaded C-Faces dataset. Corresponding codes will be updated shortly. Please be patient. Thank you very much!
  • 06/16/2020: We have released C-Digits dataset and corresponding weights.

Data Preparation

[OCDA Datasets]

First, please download C-Digits, save it to a directory, and change the dataset root in the config file accordingly. The file contains MNIST, MNIST-M, SVHN, SVHN-bal, and SynNum.

For C-Faces, please download Multi-PIE first. Since it is a proprietary dataset, we can only privide the data list we used during training here. We will update the dataset function accordingly.

Getting Started (Training & Testing)


To run experiments for both training and evaluation on the C-Digits datasets (SVHN -> Multi):

python --config ./config svhn_bal_to_multi.yaml

After training is completed, the same command will automatically evaluate the trained models.


  • We will be releasing code for C-Faces experiements very soon.


Reproduced Benchmarks and Model Zoo

NOTE: All reproduced weights need to be decompressed into results directory:


C-Digits (Results may currently have variations.)

Source MNIST (C) MNIST-M (C) USPS (C) SymNum (O) Avg. Acc Download
SVHN 89.62 64.53 81.17 87.86 80.80 model

License and Citation

The use of this software is released under BSD-3.

  title={Open Compound Domain Adaptation},
  author={Liu, Ziwei and Miao, Zhongqi and Pan, Xingang and Zhan, Xiaohang and Lin, Dahua and Yu, Stella X. and Gong, Boqing},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
Open Source Agenda is not affiliated with "OpenCompoundDomainAdaptation OCDA" Project. README Source: zhmiao/OpenCompoundDomainAdaptation-OCDA

Open Source Agenda Badge

Open Source Agenda Rating