EUVIMEDEUVIMED entdecken
Crossref

Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation

Xiaoyi Bao, Jie Qin, Siyang Sun, Xingang Wang, Yun Zheng

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (2) · 765-773

DOI: 10.1609/aaai.v38i2.27834 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Xiaoyi Bao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

For few-shot semantic segmentation, the primary task is to extract class-specific intrinsic information from limited labeled data. However, the semantic ambiguity and inter-class similarity of previous methods limit the accuracy of pixel-level foreground-background classification. To alleviate these issues, we propose the Relevant Intrinsic Feature Enhancement Network (RiFeNet). To improve the semantic consistency of foreground instances, we propose an unlabeled branch as an efficient data utilization method, which teaches the model how to extract intrinsic features robust to intra-class differences. Notably, during testing, the proposed unlabeled branch is excluded without extra unlabeled data and computation. Furthermore, we extend the inter-class variability between foreground and background by proposing a novel multi-level prototype generation and interaction module. The different-grained complementarity between global and local prototypes allows for better distinction between similar categories. The qualitative and quantitative performance of RiFeNet surpasses the state-of-the-art methods on PASCAL-5i and COCO benchmarks.

Zitieren

APA

Bao, X., Qin, J., Sun, S., Wang, X., & Zheng, Y. (2024). Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(2), 765-773. https://doi.org/10.1609/aaai.v38i2.27834

Vancouver

Bao X, Qin J, Sun S, Wang X, Zheng Y. Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(2):765-773. doi:10.1609/aaai.v38i2.27834

BibTeX
@article{Bao2024,
  author = {Bao, Xiaoyi and Qin, Jie and Sun, Siyang and Wang, Xingang and Zheng, Yun},
  title = {Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {2},
  pages = {765--773},
  doi = {10.1609/aaai.v38i2.27834}
}
Kostenlos starten →