目标检测--Accurate Single Stage Detector Using Recurrent Rolling Convolution
来源:互联网 发布:java string split 点 编辑:程序博客网 时间:2024/06/02 06:53
Accurate Single Stage Detector Using Recurrent Rolling Convolution
CVPR 2017 商汤科技关于目标检测的文献
Code: https://github.com/xiaohaoChen/rrc_detection
本文直观的理解就是对SSD 自动寻找合适 contextual information 来提升目标检测性能。
这里 single stage detectors 就是一个过程就搞定了检测,相对于 R-CNN 系列的 two stage: 候选区域提取+分类
本文首先实用数学公式分析了一下 SSD 检测存在的问题
SSD heavily relies on a strong assumption to perform well
这个强假设就是 每一层特征 对于检测目标是足够复杂的 ,包含的信息是够用的。
every Φ, by itself, has to be sophisticated enough to support the detection and the accurate localization of the objects of interest
这里的 sophistication 满足一下三点:
1)特征的尺寸足够大,包含足够的目标细节
2)将原始输入图像映射到当前特征的 特征提取函数足够的deep,这样可以得到 合适的 high level abstraction ,得到目标的抽象信息
3)特征层含有合适的contextual information,基于这些信息可以解决 overlapping objects, occluded objects, small objects, blur or saturated objects
The contextual information inˆΦ(·) means differently for different objects of interest. For instance, when detecting small objects it meansˆΦ(·) should return feature maps contain higher resolution features of this object to represent the missing details. When detecting occluded objects,
ˆΦ(·) should return feature maps contain robust abstraction of such object so that the feature is relatively invariant to occlusion. When detecting overlapping objects, ˆΦ(·) should return feature maps contain both the details of the boundary and the high level abstraction to distinguish
different objects.
这里我们提出了一个 Recurrent Rolling Convolution 来渐进的完成寻找合适的 contextual information的任务
RRC is a recurrent process in which each iteration gathers and aggregates relevant features for detection. As we discussed before, these revevant feature
contains contextual information which is critical for detecting challenging objects
KITTI 测试数据检测结果:
虽然是 single stage detector, 但是这个网络的速度应该不是很快。做不到实时检测
- 目标检测--Accurate Single Stage Detector Using Recurrent Rolling Convolution
- 目标检测--Accurate Single Stage Detector Using Recurrent Rolling Convolution
- Accurate Single Stage Detector Using Recurrent Rolling Convolution
- Accurate Single Stage Detector Using Recurrent Ring Convolution
- 目标检测--SSD: Single Shot MultiBox Detector
- [目标检测]SSD: Single Shot MultiBox Detector
- 人脸检测--SSH: Single Stage Headless Face Detector
- 目标检测,windows 下跑 SSD: Single Shot MultiBox Detector
- 目标检测--Light-Head R-CNN: In Defense of Two-Stage Object Detector
- 目标检测“Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and”
- 【深度学习:目标检测】RCNN学习笔记(10):SSD:Single Shot MultiBox Detector
- SSD+caffe︱Single Shot MultiBox Detector 目标检测+fine-tuning(二)
- 深度学习:目标检测-RCNN学习笔记:SSD:Single Shot MultiBox Detector
- 使用Windows Caffe 建立Qt工程 运行SSD(Single Shot MultiBox Detector)目标检测算法
- 目标检测方法简介:RPN(Region Proposal Network) and SSD(Single Shot MultiBox Detector)
- 目标检测之SSD(single shot multibox detector)的pytorch代码阅读总结
- 【深度学习:目标检测】RCNN学习笔记(9):OverFeat:Integrated Recognition, Localization and Detection using Convolution
- 人脸检测“A Fast and Accurate Unconstrained Face Detector”
- 重写equal 的同时为什么必须重写hashcode?
- UVa1225 DIgit Counting
- 获取CPU性能信息代码
- PetaPoco 快速上手
- 挑战 P234 poj3281
- 目标检测--Accurate Single Stage Detector Using Recurrent Rolling Convolution
- 数组和链表的区别
- 盒子弧度
- Android——EventBus3.0的使用详解
- js加减乘除丢失精度问题解决方法
- 为什么Linux的音频驱动位于sound目录下而不是driver/sound?
- VR、RTMP播放器SGPlayer原理详解
- Android和javascript相互调用
- 盒子阴影