1st Place Solutions for the UVO Challenge 2022

TL;DR

This paper presents the winning solution for the UVO Challenge 2022, utilizing a two-stage detection and segmentation approach with enhanced training techniques, achieving top performance across multiple tracks.

Contribution

The paper introduces a powerful detection and segmentation framework with pseudo-label training and transformer-based detection, leading to state-of-the-art results in the UVO Challenge.

Findings

Achieved AR@100 of 46.8 in limited data track

Achieved AR@100 of 64.7 in unlimited data track

Achieved AR@100 of 32.2 in video track

Abstract

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.