Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
January 25, 2026Remote SensingOpen Access

A Few-Shot Object Detection Framework for Remote Sensing Images Based on Adaptive Decision Boundary and Multi-Scale Feature Enhancement

View Full Paper
Ask AI
Bookmark
Share

Authors

LYLijiale YangBLBangjie LiDGDongdong Guan

Discussion

Loading...

Member takes

Overview

This framework enhances object detection in remote sensing images, improving performance through innovative techniques.

Key Points

  • To improve few-shot object detection in remote sensing images by addressing limitations of existing methods.
  • Proposed a Transfer-Stable FSOD framework, TS-FSOD.
  • Integrated Feature Enhancement Module to improve small target feature representation.
  • Utilized Adaptive Fusion Unit to enhance target features while reducing background interference.
  • Employed Dynamic Temperature-scaling Learnable Classifier for adaptive decision boundary calibration.
  • Achieved competitive performance with improvements of up to 4.30% mAP over state-of-the-art methods.
  • Demonstrated notable success in 3-shot and 5-shot detection scenarios.

Cite This Study

Yang et al. (2026) studied this question.

synapsesocial.com/papers/6975b28afeba4585c2d6e019https://doi.org/10.3390/rs18030388
View Full Paper
Ask AI
Bookmark
Share