caganselim / davisforall

This package, a modified DAVIS evaluation toolkit, assesses video multi-object segmentation models, initially tailored for DAVIS 2017. It's now versatile, allowing evaluation of any VOS dataset in the UVOS context.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

DAVIS For All - A Generic J&F Evaluation Package for UVOS

This package is a modified version of DAVIS evaluation toolkit which is used to evaluate semi-supervised and unsupervised video multi-object segmentation models for the DAVIS 2017 to evaluate ANY VOS dataset in the UVOS setting.

How to Evaluate?

In order to evaluate your unsupervised method in any dataset, execute the following command substituting results/unsupervised/rvos by the folder path that contains your results:

python evaluation_method.py

You can either pass custom parameters or default_dataset_path and default_results_path in the code.

This code also allows you to pass different folder names for the masks and image folders as well.

Citation

Please cite both papers in your publications if DAVIS or this code helps your research.

@article{Caelles_arXiv_2019,
  author = {Sergi Caelles and Jordi Pont-Tuset and Federico Perazzi and Alberto Montes and Kevis-Kokitsi Maninis and Luc {Van Gool}},
  title = {The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation},
  journal = {arXiv},
  year = {2019}
}
@article{Pont-Tuset_arXiv_2017,
  author = {Jordi Pont-Tuset and Federico Perazzi and Sergi Caelles and Pablo Arbel\'aez and Alexander Sorkine-Hornung and Luc {Van Gool}},
  title = {The 2017 DAVIS Challenge on Video Object Segmentation},
  journal = {arXiv:1704.00675},
  year = {2017}
}

About

This package, a modified DAVIS evaluation toolkit, assesses video multi-object segmentation models, initially tailored for DAVIS 2017. It's now versatile, allowing evaluation of any VOS dataset in the UVOS context.

License:BSD 3-Clause "New" or "Revised" License


Languages

Language:Python 100.0%