EUVIMEDEUVIMED entdecken
Crossref

SAPNet++: Evolving Point-Prompted Instance Segmentation With Semantic and Spatial Awareness

Zhaoyang Wei, Xumeng Han, Xuehui Yu, Xue Yang, Guorong Li, Zhenjun Han, Jianbin Jiao

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026

DOI: 10.1109/tpami.2026.3667694 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. Verfasst von Zhaoyang Wei und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Pattern Recognition, Automated. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 94 Literaturangaben. Gefördert von: Key Deployment Program of the Chinese Academy of Sciences, China, National Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single-point annotation is increasingly prominent in visual tasks for labeling cost reduction. However, it challenges tasks requiring high precision, such as the point-prompted instance segmentation (PPIS) task, which aims to estimate precise masks using single-point prompts to train a segmentation network. Due to the constraints of point annotations, granularity ambiguity and boundary uncertainty arise i.e., the difficulty distinguishing between different levels of detail (e.g., whole object vs. parts) and the challenge of precisely delineating object boundaries. Previous works have usually inherited the paradigm of mask generation along with proposal selection to achieve PPIS. However, proposal selection relies solely on category information, failing to resolve the ambiguity of different granularity. Furthermore, mask generators offer only finite discrete solutions that often deviate from actual masks, particularly at boundaries. To address these issues, we propose the Semantic-Aware Point-Prompted Instance Segmentation Network (SAPNet). It integrates Point Distance Guidance and Box Mining Strategy to tackle group and local issues caused by the point's granularity ambiguity. Additionally, we incorporate completeness scores within proposals to add spatial granularity awareness, enhancing multiple instance learning (MIL) in proposal selection termed S-MIL. The Multi-level Affinity Refinement conveys pixel and semantic clues, narrowing boundary uncertainty during mask refinement. These modules culminate in SAPNet++, mitigating point prompt's granularity ambiguity and boundary uncertainty and significantly improving segmentation performance. Extensive experiments on four challenging datasets validate the effectiveness of our methods, highlighting the potential to advance PPIS.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedPattern Recognition, AutomatedSemanticsAlgorithmsHumans

Förderung

  • Key Deployment Program of the Chinese Academy of Sciences, China
  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation

Zitieren

APA

Wei, Z., Han, X., Yu, X., Yang, X., Li, G., Han, Z., & Jiao, J. (2026). SAPNet++: Evolving Point-Prompted Instance Segmentation With Semantic and Spatial Awareness. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2026.3667694

Vancouver

Wei Z, Han X, Yu X, Yang X, Li G, Han Z, et al. SAPNet++: Evolving Point-Prompted Instance Segmentation With Semantic and Spatial Awareness. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026. doi:10.1109/tpami.2026.3667694

BibTeX
@article{Wei2026,
  author = {Wei, Zhaoyang and Han, Xumeng and Yu, Xuehui and Yang, Xue and Li, Guorong and Han, Zhenjun and Jiao, Jianbin},
  title = {SAPNet++: Evolving Point-Prompted Instance Segmentation With Semantic and Spatial Awareness},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  doi = {10.1109/tpami.2026.3667694}
}
Kostenlos starten →