Skip to content
Source code of our submission (Rank 1) for Multi-Source Domain Adaptation task in VisDA-2019
Python Shell
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
ExtractFeat Extract Feat Oct 3, 2019
FeatFusionTest FeatFusion Oct 3, 2019
dataset cyclegan Oct 3, 2019 Update Oct 10, 2019


We release the source code of our submission (Rank 1) for Multi-Source Domain Adaptation task in VisDA-2019. Details can be referred in Technical report.

All the pretrained models, synthetic data generated via CycleGAN , and submission files can be downloaded from the link.


You may need a machine with 4 GPUs and PyTorch v1.1.0 for Python 3.


Train source only models

  1. Go to the Adapt folder

  2. Train source only models

bash experiments/<DOMAIN>/<NET>/

Where <DOMAIN> is clipart or painting, <NET> is the network (e.g. senet154)

Then repeat the following procedures 4 times.

Train the end-to-end adaptation module

bash experiments/<DOMAIN>/<NET>_<phase_id>/

Extract features

  1. Copy the adaptation models to the folder ExtractFeat/experiments/<phase_id>/<DOMAIN>/<NET>/snapshot

  2. Extract features by running the scripts

bash experiments/<phase_id>/<DOMAIN>/scripts/<NET>.sh

  1. Copy the features from experiments/<phase_id>/<DOMAIN>/<NET>/<NET>_<source_and_target_domains>/result to dataset/visda2019/pkl_test/<phase_id>/<DOMAIN>/<NET>

Train the feature fusion based adaptation module

  1. Go to the FeatFusionTest folder

  2. Train feature fusion based adaptation module

bash experiments/<phase_id>/<DOMAIN>/

  1. Copy the pseudo labels file to Adapt/experiments/<DOMAIN>/<NET>_<next_phase_id> for the next adaptation.


Please cite our technical report in your publications if it helps your research:

  title={Multi-Source Domain Adaptation and Semi-Supervised Domain Adaptation with Focus on Visual Domain Adaptation Challenge 2019},
  author={Pan, Yingwei and Li, Yehao and Cai, Qi and Chen, Yang and Yao, Ting},
  booktitle={Visual Domain Adaptation Challenge},


Thanks to the domain adaptation community and the contributers of the pytorch ecosystem.

Pytorch pretrained-models Cadene and EfficientNet

You can’t perform that action at this time.