PM-VIS+: High-Performance Video Instance Segmentation without Video Annotation

Zhangjing Yang, Dun Liu, Xin Wang, Zhe Li, Barathwaj Anandan +1 more
6/28/2024
cs.CV

Official code: ldknight/PM-VIS-plus (3 stars, last commit 2024-07-07).

Abstract

Video instance segmentation requires detecting, segmenting, and tracking objects in videos, typically relying on costly video annotations. This paper introduces a method that eliminates video annotations by utilizing image datasets. The PM-VIS algorithm is adapted to handle both bounding box and instance-level pixel annotations dynamically. We introduce ImageNet-bbox to supplement missing categories in video datasets and propose the PM-VIS+ algorithm to adjust supervision based on annotation types. To enhance accuracy, we use pseudo masks and semi-supervised optimization techniques on unannotated video data. This method achieves high video instance segmentation performance without manual video annotations, offering a cost-effective solution and new perspectives for video instance segmentation applications. The code will be available in https://github.com/ldknight/PM-VIS-plus

View on arXivView PDF

Code Implementations(1)

ldknight/PM-VIS-plusOfficial100%

PM-VIS+: High-Performance Video Instance Segmentation without Video Annotation

31C++, CudaJun 17, 20242 years ago

Similar Papers

Minimizing Labeled, Maximizing Unlabeled: An Image-Driven Approach for Video Instance Segmentation

90% match2026

What is Point Supervision Worth in Video Instance Segmentation?

88% match2024

S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentation

86% match1 repo22025

VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation

85% match1 repo1.1k2026

Mask-Free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations

84% match2026

Class-agnostic 3D Segmentation by Granularity-Consistent Automatic 2D Mask Tracking

84% match2025

Cite this paper

@article{yang2024pmvis,
  title  = {PM-VIS+: High-Performance Video Instance Segmentation without Video Annotation},
  author = {Zhangjing Yang and Dun Liu and Xin Wang and Zhe Li and Barathwaj Anandan and Yi Wu},
  year   = {2024},
  eprint = {2406.19665},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.19665v1}
}

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/2406.19665.svg)](https://codeofpaper.com/paper/2406.19665)

Discussion