https://github.com/aimedical/dvis-fastinst

DVIS: Decoupled Video Instance Segmentation Framework

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
○
codemeta.json file
○
.zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org, scholar.google
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (3.9%) to scientific vocabulary

Last synced: 10 months ago · JSON representation

Repository

DVIS: Decoupled Video Instance Segmentation Framework

Basic Info

Host: GitHub
Owner: aimedical
License: mit
Language: Python
Default Branch: main
Homepage:
Size: 347 KB

Statistics

Stars: 0
Watchers: 0
Forks: 0
Open Issues: 2
Releases: 0

Fork of zhang-tao-whu/DVIS

Created over 2 years ago · Last pushed about 2 years ago

https://github.com/aimedical/DVIS-FastInst/blob/main/



# [DVIS: Decoupled Video Instance Segmentation Framework](https://arxiv.org/abs/2306.03413)
[Tao Zhang](https://scholar.google.com/citations?user=3xu4a5oAAAAJ&hl=zh-CN), XingYe Tian, [Yu Wu](https://scholar.google.com/citations?hl=zh-CN&user=23SZHUwAAAAJ), [ShunPing Ji](https://scholar.google.com/citations?user=FjoRmF4AAAAJ&hl=zh-CN), Xuebo Wang, Yuan Zhang, Pengfei Wan

[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dvis-decoupled-video-instance-segmentation/video-instance-segmentation-on-ovis-1)](https://paperswithcode.com/sota/video-instance-segmentation-on-ovis-1?p=dvis-decoupled-video-instance-segmentation)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dvis-decoupled-video-instance-segmentation/video-panoptic-segmentation-on-vipseg)](https://paperswithcode.com/sota/video-panoptic-segmentation-on-vipseg?p=dvis-decoupled-video-instance-segmentation)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dvis-decoupled-video-instance-segmentation/video-instance-segmentation-on-youtube-vis-3)](https://paperswithcode.com/sota/video-instance-segmentation-on-youtube-vis-3?p=dvis-decoupled-video-instance-segmentation)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dvis-decoupled-video-instance-segmentation/video-instance-segmentation-on-youtube-vis-1)](https://paperswithcode.com/sota/video-instance-segmentation-on-youtube-vis-1?p=dvis-decoupled-video-instance-segmentation)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dvis-decoupled-video-instance-segmentation/video-instance-segmentation-on-youtube-vis-2)](https://paperswithcode.com/sota/video-instance-segmentation-on-youtube-vis-2?p=dvis-decoupled-video-instance-segmentation)




## News
- DVIS achieved **1st place** in the VPS Track of the PVUW challenge at CVPR 2023. `2023.5.25`
- DVIS has been accepted by ICCV 2023. `2023.7.15`
- DVIS achieved **1st place** in the VIS Track of the 5th LSVOS challenge at ICCV 2023. `2023.8.15`

## Features
- DVIS is a universal video segmentation framework that supports VIS, VPS and VSS.
- DVIS can run in both online and offline modes. 
- DVIS achieved SOTA performance on YTVIS, OVIS, VIPSeg and VSPW datasets.
- DVIS can complete training and inference on GPUs with only 11G memory. 

## Demos
 
  
 

## Installation

See [Installation Instructions](INSTALL.md).

## Getting Started

See [Preparing Datasets for DVIS](datasets/README.md).

See [Getting Started with DVIS](GETTING_STARTED.md).

## Model Zoo

Trained models are available for download in the [DVIS Model Zoo](MODEL_ZOO.md).

## Citing DVIS

```BibTeX
@article{DVIS,
  title={DVIS: Decoupled Video Instance Segmentation Framework},
  author={Zhang, Tao and Tian, Xingye and Wu, Yu and Ji, Shunping and Wang, Xuebo and Zhang, Yuan and Wan, Pengfei},
  journal={arXiv preprint arXiv:2306.03413},
  year={2023}
}

@article{zhang2023vis1st,
  title={1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation},
  author={Zhang, Tao and Tian, Xingye and Zhou, Yikang and Wu, Yu and Ji, Shunping and Yan, Cilin and Wang, Xuebo and Tao, Xin and Zhang, Yuan and Wan, Pengfei},
  journal={arXiv preprint arXiv:2308.14392},
  year={2023}
}

@article{zhang2023vps1st,
  title={1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation},
  author={Zhang, Tao and Tian, Xingye and Wei, Haoran and Wu, Yu and Ji, Shunping and Wang, Xuebo and Zhang, Yuan and Wan, Pengfei},
  journal={arXiv preprint arXiv:2306.04091},
  year={2023}
}
```

## Acknowledgement

This repo is largely based on [Mask2Former](https://github.com/facebookresearch/Mask2Former), [MinVIS](https://github.com/NVlabs/MinVIS) and [VITA](https://github.com/sukjunhwang/VITA).
Thanks for their excellent works.