Semi-supervised Video Semantic Segmentation Using Unreliable Pseudo Labels for PVUW2024

Biao Wu, Diankai Zhang, Si Gao, Chengjian Zheng, Shaoli Liu +1 more
6/2/2024
cs.CV

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image. Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction,because the real-world is actually video-based rather than a static state. In this paper, we adopt semi-supervised video semantic segmentation method based on unreliable pseudo labels. Then, We ensemble the teacher network model with the student network model to generate pseudo labels and retrain the student network. Our method achieves the mIoU scores of 63.71% and 67.83% on development test and final test respectively. Finally, we obtain the 1st place in the Video Scene Parsing in the Wild Challenge at CVPR 2024.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant

85% match1 repo432026

Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation

84% match1 repo82026

Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation

84% match1 repo12026

Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentation

83% match1 repo32026

Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization

83% match1 repo42024

Multi-Level Label Correction by Distilling Proximate Patterns for Semi-supervised Semantic Segmentation

83% match2024

Cite this paper

@article{wu2024semisupervised,
  title  = {Semi-supervised Video Semantic Segmentation Using Unreliable Pseudo Labels for PVUW2024},
  author = {Biao Wu and Diankai Zhang and Si Gao and Chengjian Zheng and Shaoli Liu and Ning Wang},
  year   = {2024},
  eprint = {2406.00587},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.00587v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.00587.svg)](https://codeofpaper.com/paper/2406.00587)

Discussion