We find Mask2Former also achieves state-of-the-art performance on video instance segmentation without modifying the architecture, the loss or even the training pipeline. In this report, we show universal image segmentation architectures trivially generalize to video segmentation by directly predicting 3D segmentation volumes. Specifically, Mask2Former sets a new state-of-the-art of 60.4 AP on YouTubeVIS-2019 and 52.6 AP on YouTubeVIS-2021. We believe Mask2Former is also capable of handling video semantic and panoptic segmentation, given its versatility in image segmentation. We hope this will make state-of-the-art video segmentation research more accessible and bring more attention to designing universal image and video segmentation architectures.
@article{arxiv.2112.10764,
title = {Mask2Former for Video Instance Segmentation},
author = {Bowen Cheng and Anwesa Choudhuri and Ishan Misra and Alexander Kirillov and Rohit Girdhar and Alexander G. Schwing},
journal= {arXiv preprint arXiv:2112.10764},
year = {2021}
}
Comments
Code and models: https://github.com/facebookresearch/Mask2Former