Video Instance Segmentation (VIS) is a multi-task problem performing detection, segmentation, and tracking simultaneously. Extended from image set applications, video data additionally induces the temporal information, which, if handled appropriately, is very useful to identify and predict object motions. In this work, we design a unified model to mutually learn these tasks. Specifically, we propose two modules, named Temporally Correlated Instance Segmentation (TCIS) and Bidirectional Tracking (BiTrack), to take the benefit of the temporal correlation between the object's instance masks across adjacent frames. On the other hand, video data is often redundant due to the frame's overlap. Our analysis shows that this problem is particularly severe for the YoutubeVOS-VIS2021 data. Therefore, we propose a Multi-Source Data (MSD) training mechanism to compensate for the data deficiency. By combining these techniques with a bag of tricks, the network performance is significantly boosted compared to the baseline, and outperforms other methods by a considerable margin on the YoutubeVOS-VIS 2019 and 2021 datasets.
@article{arxiv.2106.06649,
title = {1st Place Solution for YouTubeVOS Challenge 2021:Video Instance Segmentation},
author = {Thuy C. Nguyen and Tuan N. Tang and Nam LH. Phan and Chuong H. Nguyen and Masayuki Yamazaki and Masao Yamanaka},
journal= {arXiv preprint arXiv:2106.06649},
year = {2021}
}