openset_domain_adaptation

Open-set Domain Adaptation for Image Classification

Installation

Example scripts also support all models in PyTorch-Image-Models. You also need to install timm to use PyTorch-Image-Models.

pip install timm

Dataset

Following datasets can be downloaded automatically:

• Office31
• OfficeHome
• VisDA2017

Supported Methods

Supported methods include:

• Open Set Domain Adaptation (OSBP)

Experiment and Results

The shell files give the script to reproduce the benchmarks with specified hyper-parameters. For example, if you want to train DANN on Office31, use the following script

# Train a DANN on Office-31 Amazon -> Webcam task using ResNet 50.
# Assume you have put the datasets under the path `data/office-31`, 
# or you are glad to download the datasets automatically from the Internet to this path
CUDA_VISIBLE_DEVICES=0 python dann.py data/office31 -d Office31 -s A -t W -a resnet50 --epochs 20 --seed 1 --log logs/dann/Office31_A2W

For more information please refer to Get Started for help.

Citation

If you use these methods in your research, please consider citing.

@InProceedings{OSBP,
    author = {Saito, Kuniaki and Yamamoto, Shohei and Ushiku, Yoshitaka and Harada, Tatsuya},
    title = {Open Set Domain Adaptation by Backpropagation},
    booktitle = {ECCV},
    year = {2018}
}