EUVIMEDEUVIMED entdecken
Crossref

Bridge the Intra-Class Gap: K-Shot Multi-Scale Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation

Yuanwei Liu, Nian Liu, Tao Jiang, Xiwen Yao, Rao Muhammad Anwer, Hisham Cholakkal, Junwei Han

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-12 · 47 (12) · 11003-11021

DOI: 10.1109/tpami.2025.3593816 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-12. Verfasst von Yuanwei Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: Noncommunicable Chronic Diseases-National Science and Technology Major Project, Key-Area Research and Development Program of Guangdong Province, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Few-shot segmentation (FSS) aims to accurately segment target objects in a query image using only a limited number of annotated support images. Existing approaches typically follow a paradigm that directly leverages category information from the support set to identify target objects in the query. However, these methods often ignore the category information gap between query and support images, leading to suboptimal performance when faced with images containing objects exhibiting significant intra-class diversity. To address this issue, we propose a novel framework that introduces intermediate prototypes to capture both deterministic information from the support images and adaptive knowledge from the query at multiple scales. Our framework, named the K-shot Multi-scale Intermediate Prototype Mining Transformer (KMIPMT), is based on the Transformer architecture and learns intermediate prototypes in an iterative manner, where each KMIPMT layer propagates category information from both K-shot support features and multi-scale query features to intermediate prototypes. This information is then utilized to activate the query feature map. Through repeated iterations, both intermediate prototypes and the query feature are progressively enhanced, and the final refined query feature is used for generating precise segmentation predictions. Despite its simplicity, our method achieves remarkable performance gains on standard benchmarks, including PASCAL-$5^{i}$5i, COCO-$20^{i}$20i, and FSS-1000, setting new state-of-the-art results. Furthermore, we explore several practical and challenging extensions of our method, including 3D point cloud FSS, zero-shot segmentation, weak-label FSS, and cross-domain FSS. These extensions showcase the versatility and effectiveness of our proposed KMIPMT framework across different domains and scenarios.

Förderung

  • Noncommunicable Chronic Diseases-National Science and Technology Major Project
  • Key-Area Research and Development Program of Guangdong Province
  • National Natural Science Foundation of China
  • National Science and Technology Major Project of China
  • Outstanding Doctoral Dissertation Cultivation Fund of the School of Automation
  • Northwestern Polytechnical University

Zitieren

APA

Liu, Y., Liu, N., Jiang, T., Yao, X., Anwer, R. M., Cholakkal, H., & Han, J. (2025). Bridge the Intra-Class Gap: K-Shot Multi-Scale Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(12), 11003-11021. https://doi.org/10.1109/tpami.2025.3593816

Vancouver

Liu Y, Liu N, Jiang T, Yao X, Anwer RM, Cholakkal H, et al. Bridge the Intra-Class Gap: K-Shot Multi-Scale Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(12):11003-11021. doi:10.1109/tpami.2025.3593816

BibTeX
@article{Liu2025,
  author = {Liu, Yuanwei and Liu, Nian and Jiang, Tao and Yao, Xiwen and Anwer, Rao Muhammad and Cholakkal, Hisham and Han, Junwei},
  title = {Bridge the Intra-Class Gap: K-Shot Multi-Scale Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {12},
  pages = {11003--11021},
  doi = {10.1109/tpami.2025.3593816}
}
Kostenlos starten →