Open Compound Domain Adaptation

[Project] [Paper] [Blog]

Overview

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 Pan,  Xiaohang Zhan,  Dahua Lin,  Stella X. Yu,  Boqing 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.

Requirements

• PyTorch (version >= 0.4.1)
• scikit-learn

Updates:

• 06/16/2020: We have released C-Digits dataset and corresponding weights.

Data Preparation

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.

Getting Started (Training & Testing)

C-Digits

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

python main.py --config ./config svhn_bal_to_multi.yaml

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

C-Faces

• 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:

OpenCompoundedDomainAdaptation-OCDA
    |--results

C-Digits (Results may currently have variations.)

Source	MNIST (C)	MNIST-M (C)	USPS (C)	SymNum (O)	Avg. Acc	Download
SVHN	8 w9.62	64.53	81.17	87.86	80.80	model

C-Faces (Will update soon.)

Source	C08 (C)	C09 (C)	C13 (C)	C14 (C)	C19 (O)	Avg. Acc	Download
C05							model

License and Citation

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

@inproceedings{compounddomainadaptation,
  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)},
  year={2020}
}