1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation
Mingqi Gao1,4,+, Jingnan Luo2,+, Jinyu Yang1,*, Jungong Han3,4, Feng Zheng1,2,*
1 Tapall.ai 2 Southern University of Science and Technology 3 University of Sheffield 4 University of Warwick
+ Equal Contributions, * Corresponding Authors
We test the code in the following environments, other versions may also be compatible: Python=3.9, PyTorch=1.10.1, CUDA=11.3
pip install -r requirements.txt
pip install 'git+https://github.com/facebookresearch/fvcore'
pip install -U 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
cd models/ops
python setup.py build install
cd ../..
- Download MUTR's checkpoint from HERE (Swin-L, joint-training on Ref-COCO series and Ref-YouTube-VOS).
- Run following commands to fine-tune MUTR on MeViS:
python -m torch.distributed.launch --nproc_per_node 1 --master_port 10010 --use_env train.py --freeze_text_encoder --with_box_refine --binary --dataset_file mevis --epochs 2 --lr_drop 1 --resume [MUTR checkpoint] --output_dir [output path] --mevis_path [MeViS path] --backbone swin_l_p4w7
Our checkpoint is available on Google Drive.
python inference_mevis.py --with_box_refine --binary --freeze_text_encoder --output_dir [output path] --resume [checkpoint path] --ngpu 1 --batch_size 1 --backbone swin_l_p4w7 --mevis_path [MeViS path] --split valid --sub_video_len 30 --no_sampling (optional, no sampling mode)
If you find our solution useful for your research, please consider citing with this BibTeX:
@misc{gao20241st,
title={1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation},
author={Mingqi Gao and Jingnan Luo and Jinyu Yang and Jungong Han and Feng Zheng},
year={2024},
eprint={2406.07043},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
The solution is based on MUTR and MeViS. Thanks for the authors for their efforts.