3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW
This is an incremental improvement for video semantic segmentation in computer vision, specifically for the VSPW dataset and competition.
The paper tackled video semantic segmentation by exploring backbones and heads, finding that InternImage-H with Mask2former performed best, achieving 62.60% and 64.84% mIoU on VSPW test sets to secure third place in the PVUW2023 VSS track.
In this paper, we introduce 3rd place solution for PVUW2023 VSS track. Semantic segmentation is a fundamental task in computer vision with numerous real-world applications. We have explored various image-level visual backbones and segmentation heads to tackle the problem of video semantic segmentation. Through our experimentation, we find that InternImage-H as the backbone and Mask2former as the segmentation head achieves the best performance. In addition, we explore two post-precessing methods: CascadePSP and Segment Anything Model (SAM). Ultimately, our approach obtains 62.60\% and 64.84\% mIoU on the VSPW test set1 and final test set, respectively, securing the third position in the PVUW2023 VSS track.