Year: 2021
Type: preprint
Abstract: Recently, query based deep networks catch lots of attention owing to their end-to-end pipeline and competitive results on several fundamental computer vision tasks, such as object detection, semantic segmentation, and instance segmentation. However, how to establish a query based video instance segmentation (VIS) framework with elegant architecture and strong performance remains to be settled. In this paper, we present \textbf{QueryTrack} (i.e., tracking instances as queries), a unified query based VIS framework fully leveraging the intrinsic one-to-one correspondence between instances and queries in QueryInst. The proposed method obtains 52.7 / 52.3 AP on YouTube-VIS-2019 / 2021 datasets, which wins the 2-nd place in the YouTube-VIS Challenge at CVPR 2021 \textbf{with a single online end-to-end model, single scale testing \& modest amount of training data}. We also provide QueryTrack-ResNet-50 baseline results on YouTube-VIS-2021 val set as references for the VIS community.
Source: arXiv (Cornell University)
Authors: Yang, Shusheng, Fang, Yuxin, Wang, Xinggang, Li, Yu, Shan, Ying, Feng, Bin, Liu, Wenyu
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3176180954