# 3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW

Source: [3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW](<https://www.sota2.com/research/paper/68fa6fa21e209131cea46d07>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:24:25.039Z

Authors: Shijie Chang, Zeqi Hao, Ben Kang, Xiaoqi Zhao, Jiawen Zhu, Zhenyu Chen, Lihe Zhang, Lu Zhang, Huchuan Lu

Published: 2023-06-04T07:50:38.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.02291>)

[PDF](<https://arxiv.org/pdf/2306.02291.pdf>)