Li, Xiangtai, Zhang, Wenwei, Pang, Jiangmiao, Chen, Kai, Cheng, Guangliang ORCID: 0000-0001-8686-9513, Tong, Yunhai and Loy, Chen Change
(2022)
Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation.
In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022-6-18 - 2022-6-24.
Abstract
This paper presents Video K-Net, a simple, strong, and unified framework for fully end-to-end video panoptic seg-mentation. The method is built upon K-Net, a method that unifies image segmentation via a group of learnable ker-nels. We observe that these learnable kernels from K-Net, which encode object appearances and contexts, can naturally associate identical instances across video frames. Motivated by this observation, Video K-Net learns to simultaneously segment and track 'things' and 'stuff' in a video with simple kernel-based appearance modeling and cross-temporal kernel interaction. Despite the simplicity, it achieves state-of-the-art video panoptic segmentation results on Citscapes-VPS and KITTI-STEP without bells and whistles. In particular on KITTI-STEP, the simple method can boost almost 12% relative improvements over previous methods. We also validate its generalization on video semantic segmentation, where we boost various baselines by 2% on the VSPW dataset. Moreover, we extend K-Net into clip-level video framework for video instance segmentation where we obtain 40.5% for ResNet50 backbone and 51.5% mAP for Swin-base on YouTube-2019 validation set. We hope this simple yet effective method can serve as a new flexible baseline in video segmentation.11Both code and models are released at here.
Item Type: | Conference or Workshop Item (Unspecified) |
---|---|
Divisions: | Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science |
Depositing User: | Symplectic Admin |
Date Deposited: | 14 Mar 2023 09:32 |
Last Modified: | 24 Apr 2024 11:30 |
DOI: | 10.1109/cvpr52688.2022.01828 |
Open Access URL: | https://openaccess.thecvf.com/content/CVPR2022/pap... |
Related URLs: | |
URI: | https://livrepository.liverpool.ac.uk/id/eprint/3168997 |