EUVIMEDEUVIMED entdecken
Crossref

Revisiting Pixel Erasure: A Simple Method for Weakly Supervised Video Instance Segmentation

Guixun Luo, Huilin Ai, Zhongwei Ren, Xiaojie Jin, Yunchao Wei

IEEE Transactions on Image Processing · 2026 · 35 · 11228-11240

DOI: 10.1109/tip.2026.3731974 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Guixun Luo und 4 weiteren Autor:innen. Die Arbeit nennt 93 Literaturangaben. Gefördert von: Beijing Natural Science Foundation, National Natural Science Foundation of China, Beijing Major Science and Technology Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We aim to develop a simple framework for weakly supervised video instance segmentation (VIS) without pixelwise video annotations that can match or outperform fully supervised counterparts. To this end, we revisit pixel erasure, which is a common data augmentation strategy, and reveal that it can be naturally used to resist label noise within pseudo masks. Thus, we propose PieVIS, which exploits abundant sources of image datasets and requires only box-level annotations for the video dataset. Specifically, PieVIS consists of two stages: pseudo mask generation and self-training with pixel erasure. In the first stage, PieVIS generates pseudo masks for the video data using a model trained with image datasets. Afterward, for self-training, we adopt a simple pixel erasure technique that randomly removes colour information for some regions while keeping the pseudo masks unchanged. For the first time, we show that VIS without video mask annotations can perform comparably to or even outperform state-of-the-art fully supervised methods on YouTube-VIS (YTVIS) 2019 and 2021. More importantly, we further demonstrate that the pixel erasure strategy can also advance other weakly supervised tasks that involve learning from pseudo masks.

Förderung

  • Beijing Natural Science Foundation
  • National Natural Science Foundation of China
  • Beijing Major Science and Technology Project
  • Beijing Academy of Artificial Intelligence

Zitieren

APA

Luo, G., Ai, H., Ren, Z., Jin, X., & Wei, Y. (2026). Revisiting Pixel Erasure: A Simple Method for Weakly Supervised Video Instance Segmentation. IEEE Transactions on Image Processing, 35, 11228-11240. https://doi.org/10.1109/tip.2026.3731974

Vancouver

Luo G, Ai H, Ren Z, Jin X, Wei Y. Revisiting Pixel Erasure: A Simple Method for Weakly Supervised Video Instance Segmentation. IEEE Transactions on Image Processing. 2026;35:11228-11240. doi:10.1109/tip.2026.3731974

BibTeX
@article{Luo2026,
  author = {Luo, Guixun and Ai, Huilin and Ren, Zhongwei and Jin, Xiaojie and Wei, Yunchao},
  title = {Revisiting Pixel Erasure: A Simple Method for Weakly Supervised Video Instance Segmentation},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {11228--11240},
  doi = {10.1109/tip.2026.3731974}
}
Kostenlos starten →