Complementary Local–Global Optimization for Few-Shot Object Detection in Remote Sensing

Zhang, Yutong; Lyu, Xin; Li, Xin; Zhou, Siqi; Fang, Yiwei; Ding, Chenlong; Gao, Shengkai; Chen, Jiale

doi:10.3390/rs17132136

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Complementary Local–Global Optimization for Few-Shot Object Detection in Remote Sensing

by

Yutong Zhang

¹,

Xin Lyu

^1,2,*

,

Xin Li

¹

,

Siqi Zhou

¹,

Yiwei Fang

¹,

Chenlong Ding

¹,

Shengkai Gao

¹ and

Jiale Chen

¹

College of Computer Science and Software Engineering, Hohai University, Nanjing 210024, China

²

Key Laboratory of Water Big Data Technology of Ministry of Water Resources, Hohai University, Nanjing 211106, China

^*

Author to whom correspondence should be addressed.

Remote Sens. 2025, 17(13), 2136; https://doi.org/10.3390/rs17132136 (registering DOI)

Submission received: 30 April 2025 / Revised: 5 June 2025 / Accepted: 17 June 2025 / Published: 21 June 2025

(This article belongs to the Special Issue Efficient Object Detection Based on Remote Sensing Images)

Download Versions Notes

Abstract

Few-shot object detection (FSOD) in remote sensing remains challenging due to the scarcity of annotated samples and the complex background environments in aerial images. Existing methods often struggle to capture fine-grained local features or suffer from bias during global adaptation to novel categories, leading to misclassification as background. To address these issues, we propose a framework that simultaneously enhances local feature learning and global feature adaptation. Specifically, we design an Extensible Local Feature Aggregator Module (ELFAM) that reconstructs object structures via multi-scale recursive attention aggregation. We further introduce a Self-Guided Novel Adaptation (SGNA) module that employs a teacher-student collaborative strategy to generate high-quality pseudo-labels, thereby refining the semantic feature distribution of novel categories. In addition, a Teacher-Guided Dual-Branch Head (TG-DH) is developed to supervise both classification and regression using pseudo-labels generated by the teacher model to further stabilize and enhance the semantic features of novel classes. Extensive experiments on DlOR and iSAlD datasets demonstrate that our method achieves superior performance compared to existing state-of-the-art FSOD approaches and simultaneously validate the effectiveness of all proposed components.

Keywords: few-shot learning; object detection; pseudo-label; semi-supervised learning

Share and Cite

MDPI and ACS Style

Zhang, Y.; Lyu, X.; Li, X.; Zhou, S.; Fang, Y.; Ding, C.; Gao, S.; Chen, J. Complementary Local–Global Optimization for Few-Shot Object Detection in Remote Sensing. Remote Sens. 2025, 17, 2136. https://doi.org/10.3390/rs17132136

AMA Style

Zhang Y, Lyu X, Li X, Zhou S, Fang Y, Ding C, Gao S, Chen J. Complementary Local–Global Optimization for Few-Shot Object Detection in Remote Sensing. Remote Sensing. 2025; 17(13):2136. https://doi.org/10.3390/rs17132136

Chicago/Turabian Style

Zhang, Yutong, Xin Lyu, Xin Li, Siqi Zhou, Yiwei Fang, Chenlong Ding, Shengkai Gao, and Jiale Chen. 2025. "Complementary Local–Global Optimization for Few-Shot Object Detection in Remote Sensing" Remote Sensing 17, no. 13: 2136. https://doi.org/10.3390/rs17132136

APA Style

Zhang, Y., Lyu, X., Li, X., Zhou, S., Fang, Y., Ding, C., Gao, S., & Chen, J. (2025). Complementary Local–Global Optimization for Few-Shot Object Detection in Remote Sensing. Remote Sensing, 17(13), 2136. https://doi.org/10.3390/rs17132136

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Complementary Local–Global Optimization for Few-Shot Object Detection in Remote Sensing

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI