目标检测--Enhancement of SSD by concatenating feature maps for object detection
来源:互联网 发布:淘宝水星小飞船证吗 编辑:程序博客网 时间:2024/06/13 12:04
Enhancement of SSD by concatenating feature maps for object detection
BMVC 2017
本文是对SSD 的改进,通过牺牲一点速度来提高精度,主要解决SSD 两个问题:1)同一目标多次检测,2)小目标检测率不高
改进的地方:
1)将不同尺度的 特征图 融合起来;
2)增加 feature pyramid 网络层的特征图数量;
3)因为不同尺度特征图数量一样,可以对不同尺度特征图使用一个分类器
SSD 不同尺度的特征图是独立的,没有联系起来,导致同一目标在不同尺度上都被检测出来,进而导致同一目标多次检测
ConventionalSSDvs. theproposedRainbowSSD(R-SSD)
feature concatenation
这里介绍了三种特征图融合的方式:
1) pooling, 从前往后增加特征图,归一化尺寸
2) 借鉴图像分割中的 deconvolution, 从后往前增加特征图,归一化尺寸
3)本文的 Rainbow concatenation=pooling+deconvolution,这样每一个尺度的特征图数量都是一样的,这就导致后面可以使用一个分类器在不同尺度上检测
By using a single classifier, improvement on the generalization performance can be expected, and it can be effectively used for datasets with size
imbalance or for small datasets.
Increasing number of channels
The number of channels in each convolution layer are set to be 2 to 8 times larger than the original network
不同尺寸的目标检测精度
- 目标检测--Enhancement of SSD by concatenating feature maps for object detection
- Enhancement of SSD by concatenating feature maps for object detection笔记
- 目标检测--Feature Pyramid Networks for Object Detection
- 目标检测“Feature Pyramid Networks for Object Detection”
- 快速小目标检测--Feature-Fused SSD: Fast Detection for Small Objects
- 目标检测 Feature Pyramid Networks for Object Detection(FPN)论文笔记
- 特征金字塔特征用于目标检测:Feature Pyramid Networks for Object Detection
- 视频目标检测--Flow-Guided Feature Aggregation for Video Object Detection
- 【深度学习:目标检测】RCNN学习笔记(1):Rich feature hierarchies for accurate object detection and semantic segmentat
- 【深度学习:目标检测】RCNN学习笔记(2):Rich feature hierarchies for accurate object detection and semantic segmentat
- 目标检测 R-CNN 论文笔记(Rich feature hierarchies for accurate object detection and semantic segmentation)
- 行人检测论文笔记:Fast Feature Pyramids for Object Detection?
- 行人检测论文笔记:Fast Feature Pyramids for Object Detection?
- Object Detection Networks on Convolutional Feature Maps
- Object Detection Networks on Convolutional Feature Maps
- 目标检测--Improving Object Detection With One Line of Code
- 目标检测:Improving Object Detection With One Line of Code
- 目标检测“A MultiPath Network for Object Detection”
- vue2.0入门教程-笔记2
- (人脸识别2-3)——获取人脸识别训练数据
- IntelliJ IDEA 快捷键
- python爬取csdn用户头像
- NVIDIA Jetson TX1 系列开发教程之十:V4L2+OpenCV2.4.13实现预览、拍照功能
- 目标检测--Enhancement of SSD by concatenating feature maps for object detection
- 【偶现】【reboot】【二】java.util.concurrent.TimeoutException
- JAVA连接Redis错误提示(二)
- apache
- Android Launcher启动应用程序流程源码解析
- [RK3288][Android6.0] Fuse将被SDCardFS替换
- bootstrap-table和layer
- Ubuntu17.04 编译Elastic fusion 出现CUDA8.0与GCC版本问题
- 【poj 2406】Power Strings