note：You Only Look Once:Unified, Real-Time Object Detection

Paper ：You Only Look Once:Unified, Real-Time Object Detection

what’s the problem of the paper?
Object detection

what’s the mativations of the paper?
Humans glance at an image and instantly know what objects are in the image, where they are, and how they interact. They try to make machines behave like people ! So,this paper is trying to find a fast, accurate algorithms for object detection.

The solutions of the problem:
YOLO, a new approach to object detection !
1.We implement this model as a convolutional neural network and evaluate it on the PASCAL VOC detection dataset .
2.we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities.
3.We assign one predictor to be “responsible” for predicting an object based on which prediction has the highest current IOU with the ground truth .
4.We unify the separate components of object detection into a single neural network.
And so on…

The contributions and comments of the paper:
This paper resents a new approach to object detection,which can be optimized end-to-end directly on detection performance.
What’s more, YOLO pushes the state-of-the-art inreal-time object detection. YOLO also generalizes well to new domains making it ideal for applications that rely on fast, robust object detection.
Fast YOLO is the fastest general-purpose object detector in the literature ！！！

原文地址：https://www.baidu.com/link?url=edJE8-SmizX-G2PHBmJxz3li2_e4S_NS3P-BDGETBDyLHPxynzlwN_gAHwCJ7E94&wd=&eqid=b1ddb2a00003bad7000000065ed62135