The Runner-up Solution for YouTube-VIS Long Video Challenge 2022
This is an incremental improvement for researchers in video instance segmentation, focusing on enhancing temporal consistency in long videos.
The authors tackled video instance segmentation on long videos by using an existing online method (IDOL) enhanced with pseudo labels for contrastive learning, achieving 40.2 AP on the YouTube-VIS 2022 dataset and securing second place in the challenge.
This technical report describes our 2nd-place solution for the ECCV 2022 YouTube-VIS Long Video Challenge. We adopt the previously proposed online video instance segmentation method IDOL for this challenge. In addition, we use pseudo labels to further help contrastive learning, so as to obtain more temporally consistent instance embedding to improve tracking performance between frames. The proposed method obtains 40.2 AP on the YouTube-VIS 2022 long video dataset and was ranked second place in this challenge. We hope our simple and effective method could benefit further research.