Contextual Distribution Alignment via Correlation Contrasting for Domain Generalization

Datasets

Our code supports the following dataset:

• Office-31
• Office-Home
• Office-Caltech
• PACS
• Digit-Five
• VLCS

If you want to use your own dataset, please organize your data in the following structure.

RootDir
└───Domain1Name
│   └───Class1Name
│       │   file1.jpg
│       │   file2.jpg
│       │   ...
│   ...
└───Domain2Name
|   ...    

And then, modifty util/util.py to contain the dataset.

Usage

1. Modify the file in the scripts
2. The main script file is train.py, which can be runned by using run.sh from scripts/run.sh: cd scripts; bash run.sh.

Customization

It is easy to design your own method following the steps:

1. Add your method (a Python file) to alg/algs, and add the reference to it in the alg/alg.py

2. Modify utils/util.py to make it adapt your own parameters

3. Midify scripts/run.sh and execuate it

Great thanks to DeepDG. Our code is based on this project and extends.