UPDATES:
- [2020/06/15] Update results for DAVIS-17 test-dev set!
- [2020/03/04] Update results for DAVIS-17 validation set!
- [2019/11/17] Codes released!
This is a PyTorch implementation of our MATNet for unsupervised video object segmentation.
Motion-Attentive Transition for Zero-Shot Video Object Segmentation. [Arxiv] [TIP]
The training and testing experiments are conducted using PyTorch 1.0.1 with a single GeForce RTX 2080Ti GPU with 11GB Memory.
Other minor Python modules can be installed by running
pip install -r requirements.txt
git clone --recursive https://github.com/tfzhou/MATNet.git
In the paper, we use the following two public available dataset for training. Here are some steps to prepare the data:
-
DAVIS-17: we use all the data in the train subset of DAVIS-16. However, please download DAVIS-17 to fit the code. It will automatically choose the subset of DAVIS-16 for training.
-
YoutubeVOS-2018: we sample the training data every 10 frames in YoutubeVOS-2018. We use the dataset version with 6fps rather than 30fps.
-
Create soft links:
cd data; ln -s your/davis17/path DAVIS2017; ln -s your/youtubevos/path YouTubeVOS_2018;
I have provided some matlab scripts to generate edge annotations from mask. Please run data/run_davis2017.m
and data/run_youtube.m
.
I have provided the pytorch codes to generate HED results for the two datasets (see 3rdparty/pytorch-hed
).
Please run run_davis.py
and run_youtube.py
.
The codes are borrowed from https://github.com/sniklaus/pytorch-hed.
I have provided the pytorch codes to generate optical flow results for the two datasets (see 3rdparty/pytorch-pwc
).
Please run run_davis_flow.py
and run_youtubevos_flow.py
.
The codes are borrowed from https://github.com/sniklaus/pytorch-pwc.
Please follow the setup section to install cupy
.
warning: Total size of optical flow results of Youtube-VOS is more than 30GB.
Once all data is prepared, please run python train_MATNet.py
for training.
- Run
python test_MATNet.py
to obtain the saliency results on DAVIS-16 val set. - Run
python apply_densecrf_davis.py
for binary segmentation results.
- The segmentation results on DAVIS-16 and Youtube-objects can be downloaded from Google Drive.
- The segmentation results on DAVIS-17 val can be downloaded from Google Drive. We achieved 58.6 in terms of Mean J&F.
- The segmentation results on DAVIS-17 test-dev can be downloaded from Google Drive. We achieved 59.8 in terms of Mean J&F. The method also achieved the second place in DAVIS-20 unsupervised object segmentation challenge. Please refer to paper for more details of our challenge solution.
The pre-trained model can be downloaded from Google Drive.
If you find MATNet useful for your research, please consider citing the following papers:
@inproceedings{zhou2020motion,
title={Motion-Attentive Transition for Zero-Shot Video Object Segmentation},
author={Zhou, Tianfei and Wang, Shunzhou and Zhou, Yi and Yao, Yazhou and Li, Jianwu and Shao, Ling},
booktitle={Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI)},
year={2020},
pages={13066--13073}
}
@article{zhou2020matnet,
title={MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object Segmentation},
author={Zhou, Tianfei and Li, Jianwu and Wang, Shunzhou and Tao, Ran and Shen, Jianbing},
journal={IEEE Transactions on Image Processing},
volume={29},
pages={8326-8338},
year={2020}
}
@article{DAVIS2020-Unsupervised-2nd,
author = {T. Zhou, W. Wang, Y. Yao, J. Shen},
title = {Target-Aware Adaptive Tracking for Unsupervised Video Object Segmentation},
journal = {The 2020 DAVIS Challenge on Video Object Segmentation - CVPR Workshops},
year = {2020}
}