Object Detection《SSP-Net》笔记（2）

最新推荐文章于 2022-05-06 18:30:33 发布

3602138103

最新推荐文章于 2022-05-06 18:30:33 发布

阅读量391

点赞数

分类专栏：深度学习之图像处理

本文链接：https://blog.csdn.net/qq_27163197/article/details/78365870

版权

深度学习之图像处理专栏收录该内容

18 篇文章 0 订阅

订阅专栏

Spatial pyramid pooling in deep convolutional networks for visual recognition

说明：compute the feature maps from the entire image only once, and then pool features in arbitrary regions (sub-images) to generate fixed-length representations for training the detectors.
这里写图片描述

Introduction

直接输入整图，所有区域共享卷积计算;在Conv5层输出上提取所有区域的特征
spatial pyramid pooling (SPP)【空间金字塔池化】
1，The SPP layer pools the features and generates fixed length outputs, which are then fed into the fully connected layers (or other classifiers)。[替换Conv5的Pooling层]
这里写图片描述

Training the Network

1，Single-size training：
a fixed-size input (224×224) cropped。
这里写图片描述
2，Multi-size training
We consider two sizes: 180×180 in addition to 224×224. Rather than crop a smaller 180×180
region, we resize the aforementioned 224×224 region to 180×180.