EUVIMEDEUVIMED entdecken
Crossref

SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation

Shi-Feng Peng, Guolei Sun, Yong Li, Hongsong Wang, Guo-Sen Xie

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (6) · 6488-6496

DOI: 10.1609/aaai.v39i6.32695 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Shi-Feng Peng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The primary challenge of cross-domain few-shot segmentation (CD-FSS) is the domain disparity between the training and inference phases, which can exist in either the input data or the target classes. Previous models struggle to learn feature representations that generalize to various unknown domains from limited training domain samples. In contrast, the large-scale visual model SAM, pre-trained on tens of millions of images from various domains and classes, possesses excellent generalizability. In this work, we propose a SAM-aware graph prompt reasoning network (GPRN) that fully leverages SAM to guide CD-FSS feature representation learning and improve prediction accuracy. Specifically, we propose a SAM-aware prompt initialization module (SPI) to transform the masks generated by SAM into visual prompts enriched with high-level semantic information. Since SAM tends to divide an object into many sub-regions, this may lead to visual prompts representing the same semantic object having inconsistent or fragmented features. We further propose a graph prompt reasoning (GPR) module that constructs a graph among visual prompts to reason about their interrelationships and enable each visual prompt to aggregate information from similar prompts, thus achieving global semantic consistency. Subsequently, each visual prompt embeds its semantic information into the corresponding mask region to assist in feature representation learning. To refine the segmentation mask during testing, we also design a non-parameter adaptive point selection module (APS) to select representative point prompts from query predictions and feed them back to SAM to refine inaccurate segmentation results. Experiments on four standard CD-FSS datasets demonstrate that our method establishes new state-of-the-art results.

Zitieren

APA

Peng, S., Sun, G., Li, Y., Wang, H., & Xie, G. (2025). SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(6), 6488-6496. https://doi.org/10.1609/aaai.v39i6.32695

Vancouver

Peng S, Sun G, Li Y, Wang H, Xie G. SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(6):6488-6496. doi:10.1609/aaai.v39i6.32695

BibTeX
@article{Peng2025,
  author = {Peng, Shi-Feng and Sun, Guolei and Li, Yong and Wang, Hongsong and Xie, Guo-Sen},
  title = {SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {6},
  pages = {6488--6496},
  doi = {10.1609/aaai.v39i6.32695}
}
Kostenlos starten →