EUVIMEDEUVIMED entdecken
Crossref

Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation

Suho Park, SuBeen Lee, Hyun Seok Seong, Jaejoon Yoo, Jae-Pil Heo

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (6) · 6425-6433

DOI: 10.1609/aaai.v39i6.32688 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Suho Park und 4 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose Foreground-Covering Prototype Generation and Matching to resolve Few-Shot Segmentation (FSS), which aims to segment target regions in unlabeled query images based on labeled support images. Unlike previous research, which typically estimates target regions in the query using support prototypes and query pixels, we utilize the relationship between support and query prototypes. To achieve this, we utilize two complementary features: SAM Image Encoder features for pixel aggregation and ResNet features for class consistency. Specifically, we construct support and query prototypes with SAM features and distinguish query prototypes of target regions based on ResNet features. For the query prototype construction, we begin by roughly guiding foreground regions within SAM features using the conventional pseudo-mask, then employ iterative cross-attention to aggregate foreground features into learnable tokens. Here, we discover that the cross-attention weights can effectively alternate the conventional pseudo-mask. Therefore, we use the attention-based pseudo-mask to guide ResNet features to focus on the foreground, then infuse the guided ResNet feature into the learnable tokens to generate class-consistent query prototypes. The generation of the support prototype is conducted symmetrically to that of the query one, with the pseudo-mask replaced by the ground-truth mask. Finally, we compare these query prototypes with support ones to generate prompts, which subsequently produce object masks through the SAM Mask Decoder. Our state-of-the-art performances on various datasets validate the effectiveness of the proposed method for FSS.

Zitieren

APA

Park, S., Lee, S., Seong, H. S., Yoo, J., & Heo, J. (2025). Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(6), 6425-6433. https://doi.org/10.1609/aaai.v39i6.32688

Vancouver

Park S, Lee S, Seong HS, Yoo J, Heo J. Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(6):6425-6433. doi:10.1609/aaai.v39i6.32688

BibTeX
@article{Park2025,
  author = {Park, Suho and Lee, SuBeen and Seong, Hyun Seok and Yoo, Jaejoon and Heo, Jae-Pil},
  title = {Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {6},
  pages = {6425--6433},
  doi = {10.1609/aaai.v39i6.32688}
}
Kostenlos starten →