Learning Rich Features at High-Speed for Single-Shot Object Detection 论文笔记

时间 2020-12-30

标签目标检测繁體版

原文原文链接

前言目前的single-stage目标检测器依然存在两个问题：在检测小目标时，性能不是很好。比如RetinaNet在检测COCO上的大目标时能达到47的AP，而小目标的AP只有14；大多数single-stage检测器采用在ImageNet上经过预训练的backbone来进行分类任务，然后利用目标检测数据集进行微调以实现快速收敛。但是分类任务和定位任务之间仍存在较大差异，尤其是在IoU阈值较

>>阅读原文<<

1. 【论文笔记】：Learning Rich Features at High-Speed for Single-Shot Object Detection
2. 论文笔记：Learning Region Features for Object Detection
3. 《Learning Rich Features at High-Speed for Single-Shot Object Detection》笔记
4. Learning Region Features for Object Detection
5. Learning Rich Features from RGB-D Images for Object Detection and Segmentation(ECCV2014)
6. 论文笔记：Rich feature hierarchies for accurate object detection and semantic segmentation
7. 【论文阅读笔记】Rich feature hierarchies for accurate object detection and semantic segmentation
8. 论文：Rich feature hierarchies for accurate object detection and semantic segmentation 个人笔记
9. 论文笔记：Rich feature hierarchies for accurate object detection and semantic segmentation(R-CNN)
10. Richer Convolutional Features for Edge Detection论文笔记
更多相关文章...
• Scala for循环 - Scala教程
• ASP.NET Razor - 标记 - ASP.NET 教程
• Tomcat学习笔记（史上最全tomcat学习笔记）
• Scala 中文乱码解决

最新文章

1. 添加voicebox
2. Java 8u40通过Ask广告软件困扰Mac用户
3. 数字图像处理入门[1/2]（从几何变换到图像形态学分析）
4. 如何调整MathType公式的字体大小
5. mAP_Roi
6. GCC编译器安装（windows环境）
7. LightGBM参数及分布式
8. 安装lightgbm以及安装xgboost
9. 开源matpower安装过程
10. 从60%的BI和数据仓库项目失败，看出从业者那些不堪的乱象

本站公众号

欢迎关注本站公众号,获取更多信息

1. 【论文笔记】：Learning Rich Features at High-Speed for Single-Shot Object Detection
2. 论文笔记：Learning Region Features for Object Detection
3. 《Learning Rich Features at High-Speed for Single-Shot Object Detection》笔记
4. Learning Region Features for Object Detection
5. Learning Rich Features from RGB-D Images for Object Detection and Segmentation(ECCV2014)
6. 论文笔记：Rich feature hierarchies for accurate object detection and semantic segmentation
7. 【论文阅读笔记】Rich feature hierarchies for accurate object detection and semantic segmentation
8. 论文：Rich feature hierarchies for accurate object detection and semantic segmentation 个人笔记
9. 论文笔记：Rich feature hierarchies for accurate object detection and semantic segmentation(R-CNN)
10. Richer Convolutional Features for Edge Detection论文笔记

>>更多相关文章<<