CNN大类与CV

机器学习在图像检测方面主要有  分类、目标检测、分割  三个任务

分类——CNN

只是把图片做classify

LeNet,ResLet

---

目标检测——SSD

更进一步，在图像上标出object的位置，并且object可能不止一个

Understanding SSD MultiBox — Real-Time Object Detection In Deep Learning

“A few years ago, by exploiting some of the leaps made possible in computer vision via CNNs, researchers developed R-CNNs to deal with the tasks of object detection, localization and classification. 

Fortunately, in the last few years, new architectures were created to address the bottlenecks of R-CNN and its successors, enabling real-time object detection. The most famous ones are YOLO (You Only Look Once) and SSD MultiBox (Single Shot Detector). ”

---

UNet——分割

像素级别的识别

FCN,UNet

 

R-CNN  Fast-R-CNN   Faster-R-CNN    Mask-Faster-R-CNN

RCNN- 将CNN引入目标检测的开山之作

RCNN (论文：Rich feature hierarchies for accurate object detection and semantic segmentation) 是将CNN方法引入目标检测领域， 大大提高了目标检测效果，可以说改变了目标检测领域的主要研究思路， 紧随其后的系列文章：（ RCNN）,Fast RCNN, Faster RCNN 代表该领域当前最高水准。

这个领域现在可是变得太快了，过一两年就把前面的给颠覆了。