Video Instance Segmentation 2019: A winning approach for combined Detection, Segmentation, Classification and Tracking

Video Instance Segmentation (VIS) is the task of localizing all objects in a video, segmenting them, tracking them throughout the video and classifying them into a set of pre-defined classes. In this work, divide VIS into these four parts: detection, segmentation, tracking and. classification. We then develop algorithms for petforming each of these four sub tasks individually, and combine these into a complete solution for VIS. Our solution is an adaptation of Un-OVOST, the current best petforming algorithm for Unsupervised Video Object Segmentation, to this VIS task. We benchmark our algorithm on the 2019 YouTube-VIS Challenge, where we obtain first place with an mAP score of 46.7%.