1st Place Solution for YouTubeVOS Challenge 2021:Video Instance Segmentation
This work addresses video instance segmentation for computer vision applications, representing an incremental improvement with specific gains in performance.
The authors tackled the Video Instance Segmentation (VIS) problem by designing a unified model with two modules (TCIS and BiTrack) to leverage temporal correlations and a Multi-Source Data training mechanism to address data redundancy, achieving first place on the YouTubeVOS-VIS 2021 challenge and outperforming other methods on the 2019 and 2021 datasets.
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.