EUVIMEDEUVIMED entdecken
Crossref

Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label

Xinliang Zhang, Lei Zhu, Hangzhou He, Lujia Jin, Yanye Lu

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (7) · 7332-7340

DOI: 10.1609/aaai.v38i7.28563 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Xinliang Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Scribble-based weakly-supervised semantic segmentation using sparse scribble supervision is gaining traction as it reduces annotation costs when compared to fully annotated alternatives. Existing methods primarily generate pseudo-labels by diffusing labeled pixels to unlabeled ones with local cues for supervision. However, this diffusion process fails to exploit global semantics and class-specific cues, which are important for semantic segmentation. In this study, we propose a class-driven scribble promotion network, which utilizes both scribble annotations and pseudo-labels informed by image-level classes and global semantics for supervision. Directly adopting pseudo-labels might misguide the segmentation model, thus we design a localization rectification module to correct foreground representations in the feature space. To further combine the advantages of both supervisions, we also introduce a distance entropy loss for uncertainty reduction, which adapts per-pixel confidence weights according to the reliable region determined by the scribble and pseudo-label's boundary. Experiments on the ScribbleSup dataset with different qualities of scribble annotations outperform all the previous methods, demonstrating the superiority and robustness of our method. The code is available at https://github.com/Zxl19990529/Class-driven-Scribble-Promotion-Network.

Zitieren

APA

Zhang, X., Zhu, L., He, H., Jin, L., & Lu, Y. (2024). Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label. Proceedings of the AAAI Conference on Artificial Intelligence, 38(7), 7332-7340. https://doi.org/10.1609/aaai.v38i7.28563

Vancouver

Zhang X, Zhu L, He H, Jin L, Lu Y. Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(7):7332-7340. doi:10.1609/aaai.v38i7.28563

BibTeX
@article{Zhang2024,
  author = {Zhang, Xinliang and Zhu, Lei and He, Hangzhou and Jin, Lujia and Lu, Yanye},
  title = {Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {7},
  pages = {7332--7340},
  doi = {10.1609/aaai.v38i7.28563}
}
Kostenlos starten →