咨询与建议

看过本文的还看了

相关文献

该作者的其他文献

文献详情 >Advancing Fine-Grained Few-Sho... 收藏

Advancing Fine-Grained Few-Shot Object Detection on Remote Sensing Images with Decoupled Self-Distillation and Progressive Prototype Calibration

作     者:Guo, Hao Liu, Yanxing Pan, Zongxu Hu, Yuxin 

作者机构:Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China Chinese Acad Sci Key Lab Technol Geospatial Informat Proc & Applica Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China Key Lab Target Cognit & Applicat Technol Beijing 100190 Peoples R China 

出 版 物:《REMOTE SENSING》 (Remote Sens.)

年 卷 期:2025年第17卷第3期

页      面:495-495页

核心收录:

学科分类:0830[工学-环境科学与工程(可授工学、理学、农学学位)] 1002[医学-临床医学] 070801[理学-固体地球物理学] 07[理学] 08[工学] 0708[理学-地球物理学] 0816[工学-测绘科学与技术] 

基  金:the Youth Innovation Promotion Association, Chinese Academy of Sciences (CAS) Youth Innovation Promotion Association, Chinese Academy of Sciences (CAS) 

主  题:remote sensing images few-shot object detection fine-grained object detection self-distillation prototype calibration 

摘      要:In data-scarcity scenarios, few-shot object detection (FSOD) methods exhibit a notable advantage in alleviating the over-fitting problem. Currently, research on FSOD in the field of remote sensing is advancing rapidly and FSOD methods based on the fine-tuning paradigm have initially displayed their excellent performance. However, existing fine-tuning methods often encounter classification confusion issues. This is potentially because of the shortage of explicit modeling for transferable common knowledge and the biased class distribution, especially for fine-grained targets with higher inter-class similarity and intra-class variance. In view of this, we first propose a decoupled self-distillation (DSD) method to construct class prototypes in two decoupled feature spaces and measure inter-class correlations as soft labels or aggregation weights. To ensure a robust set of class prototypes during the self-distillation process, we devise a feature filtering module (FFM) to preselect high-quality class representative features. Furthermore, we introduce a progressive prototype calibration module (PPCM) with two steps, compensating the base prototypes with the prior base distribution and then calibrating the novel prototypes with adjacent calibrated base prototypes. Experiments on MAR20 and customized SHIP20 datasets have demonstrated the superior performance of our method compared to other existing advanced FSOD methods, simultaneously confirming the effectiveness of all proposed components.

读者评论 与其他读者分享你的观点

用户名:未登录
我的评分