Mining High-Quality Pseudoinstance Soft Labels for Weakly Supervised Object Detection in Remote Sensing Images
Author:
Affiliation:
1. College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou, China
2. School of Automation, Northwestern Polytechnical University, Xi’an, China
Funder
National Natural Science Foundation of China
Key Science and Technology Program of Henan Province
Development Program of Shaanxi Province
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
General Earth and Planetary Sciences,Electrical and Electronic Engineering
Link
http://xplorestaging.ieee.org/ielx7/36/10006360/10102106.pdf?arnumber=10102106
Reference61 articles.
1. FAR-Net: Fast Anchor Refining for Arbitrary-Oriented Object Detection
2. Path Aggregation Network for Instance Segmentation
3. Background prior-based salient object detection via deep reconstruction residual;han;IEEE Trans Circuits Syst Video Technol,2014
4. Focal Loss for Dense Object Detection
5. Feature Enhancement Network for Object Detection in Optical Remote Sensing Images
Cited by 32 articles. 订阅此论文施引文献 订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. DMF2Net: Dynamic multi-level feature fusion network for heterogeneous remote sensing image change detection;Knowledge-Based Systems;2024-09
2. Enhanced Attention Guided Teacher–Student Network for Weakly Supervised Object Detection;Neurocomputing;2024-09
3. Improving remote sensing object detection by using feature extraction and rotational equivariant attention;International Journal of Remote Sensing;2024-05-24
4. Mining local and global spatiotemporal features for tactile object recognition;Frontiers in Neurorobotics;2024-05-03
5. Improving Oriented Object Detection by Scene Classification and Task-Aligned Focal Loss;Mathematics;2024-04-28
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3