1st Place Solutions for the UVO Challenge 2022
This work addresses video object segmentation for computer vision researchers, but it is incremental as it builds on prior champion methods.
The paper tackled the UVO Challenge 2022 by using a two-stage detection and segmentation approach with enhanced models and pseudo-label training, achieving first place with AR@100 scores of 46.8, 64.7, and 32.2 across different tracks.
This paper describes the approach we have taken in the challenge. We still adopted the two-stage scheme same as the last champion, that is, detection first and segmentation followed. We trained more powerful detector and segmentor separately. Besides, we also perform pseudo-label training on the test set, based on student-teacher framework and end-to-end transformer based object detection. The method ranks first on the 2nd Unidentified Video Objects (UVO) challenge, achieving AR@100 of 46.8, 64.7 and 32.2 in the limited data frame track, unlimited data frame track and video track respectively.