Bidirectional Learning for Domain Adaptation of Semantic Segmentation (CVPR 2019)

A pytorch implementation of BDL. If you use this code in your research please consider citing

@article{li2019bidirectional, title={Bidirectional Learning for Domain Adaptation of Semantic Segmentation}, author={Li, Yunsheng and Yuan, Lu and Vasconcelos, Nuno}, journal={arXiv preprint arXiv:1904.10620}, year={2019} }

Requirements

Hardware: PC with NVIDIA Titan GPU.
Software: Ubuntu 16.04, CUDA 9.2, Anaconda2, pytorch 0.4.0
Python package
- conda install pytorch=0.4.0 torchvision cuda91 -y -c pytorch
- pip install tensorboard tensorboardX

Datasets

Download the GTA5 Dataset as source dataset
Download the Cityscapes Dataset as target dataset

Train adaptive segmenation network in BDL

Transferred images for CityScapes dataset can be found:
- GTA5 as CityScapes (DeepLab)
Initial model can be downloaded from DeepLab-V2
Training example (without self-supervised learning):

python BDL.py --snapshot-dir ./snapshots/gta2city \
              --init-weights /path/to/inital_weights \
              --num-steps-stop 80000 \
              --model DeepLab

Training example (with self-supervised learning):
- Download the model SSL_step1 or SSL_step2 to generate pseudo labels for CityScapes dataset and then run:

python SSL.py --data-list-target /path/to/dataset/cityscapes_list/train.txt \
              --restore-from /path/to/SSL_step1_or_SSL_step2 \
              --model DeepLab \ 
              --save /path/to/cityscapes/cityscapes_ssl \
              --set train

With the pseudo labels, the adaptive segmenation model can be trained as:

python BDL.py --data-label-folder-target pseudo_label_folder_name \ 
              --snapshot-dir ./snapshots/gta2city_ssl \
              --init-weights /path/to/inital_weights \
              --num-steps-stop 120000 \
              --model DeepLab

Evaluation

The pre-trained model can be downloaded here GTA5_deeplab. You can use the pre-trained model or your own model to make a test as following:

python evaluation.py --restore-from ./snapshots/gta2city \
                     --save /path/to/cityscapes/results

Others

The different initial models can be downloaded here:

Download SYNTHIA as CityScapes
Download initial weights of GTA5 for VGG16-FCN
Download initial weights of SYNTHIA for VGG16-FCN

If you want to use BDL for SYNTHIA dataset or use VGG-FCN model, you can assign '--source synthia' or '--model VGG' The model for SYNTHIA with DeepLab or VGG can be downloaded here to reproduce the results in the paper:

Download SYNTHIA_deeplab
Download SYNTHIA_VGG

The model for GTA5 with VGG can be downloaded here to reproduce the results in the paper:

city292/BDL