Negative-Core Sample Knowledge Distillation for Oriented Object Detection in Remote Sensing Image

IF 8.6 1区 地球科学 Q1 ENGINEERING, ELECTRICAL & ELECTRONIC IEEE Transactions on Geoscience and Remote Sensing Pub Date : 2024-11-05 DOI:10.1109/TGRS.2024.3492046
Wenhui Zhang;Yidan Zhang;Feilong Huang;Xiyu Qi;Lei Wang;Xiaoxuan Liu
{"title":"Negative-Core Sample Knowledge Distillation for Oriented Object Detection in Remote Sensing Image","authors":"Wenhui Zhang;Yidan Zhang;Feilong Huang;Xiyu Qi;Lei Wang;Xiaoxuan Liu","doi":"10.1109/TGRS.2024.3492046","DOIUrl":null,"url":null,"abstract":"Knowledge distillation (KD) has been one of the most effective methods for enhancing the performance of lightweight detectors, crucial for remote sensing edge intelligence models. However, many mainstream distillation methods that are centered around the paradigm of distilling positive samples show weak exploitation of the student’s potential. This arises due to these methods overlooking the core teacher-student difference in remote sensing scenarios with vast and object-similar backgrounds. In this article, from the point of distillation sample and knowledge hierarchy, we design a negative-core sample knowledge distillation (NSD) method for improving the performance of the lightweight object detection model. Specifically, a negative-core sample (NCS) is innovatively employed to transfer effective background discrimination knowledge for bridging the core difference. KD for NCS across four levels—pixel, logit, box, and angle—are customized to fully leverage the teacher’s insights. Category direction estimation (CE) is incorporated into the angle KD to convey NCS-oriented knowledge more effectively. Extensive experiments conducted on multiple remote sensing datasets achieve state-of-the-art (SOTA) performance, demonstrating the effectiveness of the proposed NSD. Codes are available at \n<uri>https://github.com/Changan00/NSD</uri>\n.","PeriodicalId":13213,"journal":{"name":"IEEE Transactions on Geoscience and Remote Sensing","volume":"62 ","pages":"1-18"},"PeriodicalIF":8.6000,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Geoscience and Remote Sensing","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10744590/","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

Knowledge distillation (KD) has been one of the most effective methods for enhancing the performance of lightweight detectors, crucial for remote sensing edge intelligence models. However, many mainstream distillation methods that are centered around the paradigm of distilling positive samples show weak exploitation of the student’s potential. This arises due to these methods overlooking the core teacher-student difference in remote sensing scenarios with vast and object-similar backgrounds. In this article, from the point of distillation sample and knowledge hierarchy, we design a negative-core sample knowledge distillation (NSD) method for improving the performance of the lightweight object detection model. Specifically, a negative-core sample (NCS) is innovatively employed to transfer effective background discrimination knowledge for bridging the core difference. KD for NCS across four levels—pixel, logit, box, and angle—are customized to fully leverage the teacher’s insights. Category direction estimation (CE) is incorporated into the angle KD to convey NCS-oriented knowledge more effectively. Extensive experiments conducted on multiple remote sensing datasets achieve state-of-the-art (SOTA) performance, demonstrating the effectiveness of the proposed NSD. Codes are available at https://github.com/Changan00/NSD .
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
用于遥感图像中定向物体检测的负核样本知识提炼
知识蒸馏(KD)是提高轻量级探测器性能的最有效方法之一,对遥感边缘智能模型至关重要。然而,许多以提炼正样本为核心的主流提炼方法对学生潜能的挖掘较弱。这是因为这些方法忽视了在遥感场景中师生的核心差异,而遥感场景的背景广阔且对象相似。本文从提炼样本和知识层次的角度出发,设计了一种负核样本知识提炼(NSD)方法,以提高轻量级物体检测模型的性能。具体来说,我们创新性地采用了负核心样本(NCS)来传输有效的背景判别知识,以弥合核心差异。针对像素、对数、方框和角度四个层面的 NCS KD 进行了定制,以充分利用教师的洞察力。在角度 KD 中加入了类别方向估计 (CE),以更有效地传达以非殖民化为导向的知识。在多个遥感数据集上进行的广泛实验取得了最先进(SOTA)的性能,证明了所提出的 NSD 的有效性。代码见 https://github.com/Changan00/NSD。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
IEEE Transactions on Geoscience and Remote Sensing
IEEE Transactions on Geoscience and Remote Sensing 工程技术-地球化学与地球物理
CiteScore
11.50
自引率
28.00%
发文量
1912
审稿时长
4.0 months
期刊介绍: IEEE Transactions on Geoscience and Remote Sensing (TGRS) is a monthly publication that focuses on the theory, concepts, and techniques of science and engineering as applied to sensing the land, oceans, atmosphere, and space; and the processing, interpretation, and dissemination of this information.
期刊最新文献
Improve OMI Observations on Ground-Level NO 2 using Multiple Observations, Simulations and Machine Learning Estimation of carbon storage based on UAV multispectral photogrammetry: An offshore islands study in Pearl River Delta PVMD-Net: A Deep Network for Synchronization Error Compensation in Bistatic Imaging Radar DSCH-Net: Diffusion-State-Contextual Hybrid Network for Physics-Inspired and Direction-Aware Dehazing of Remote Sensing Imagery Monte Carlo Simulation-Based Echo Modeling of Inhomogeneous Ice-Phase Precipitation Particles for Airborne Dual-Polarization Weather Radar
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1