Explore
For Enterprise
Join for Free
Log In

deeplearning.ai
AI is everywhere. Now there’s AI for Everyone.
AI is not only for engineers. This non-technical course will help you apply AI in your own organization.
University of Pennsylvania
Learn the foundations of Fintech from experts at Wharton
Master the fundamentals of financial technologies through case studies of Wharton-led companies.

浏览 Coursera 的全部课程

浏览
顶级课程
企业版
登录
免费加入

Faster R-CNN

Loading...

Deep Learning in Computer Vision

国立高等经济大学

3.8（182 个评分） | 26K 名学生已注册

课程 5（共 7 门，高级机器学习专项课程）

Deep learning added a huge boost to the already rapidly developing field of computer vision. With deep learning, a lot of new applications of computer vision techniques have been introduced and are now becoming parts of our everyday lives. These include face recognition and indexing, photo stylization or machine vision in self-driving cars. The goal of this course is to introduce students to computer vision, starting from basics and then turning to more modern deep learning models. We will cover both image and video recognition, including image classification and annotation, object recognition and image search, various object detection techniques, motion estimation, object tracking in video, human action recognition, and finally image stylization, editing and new image generation. In course project, students will learn how to build face recognition and manipulation system to understand the internal mechanics of this technology, probably the most renown and often demonstrated in movies and TV-shows example of computer vision and AI. Do you have technical problems? Write to us: coursera@hse.ru

查看授课大纲

审阅

3.8（182 个评分）

5 stars
95 ratings
4 stars
22 ratings
3 stars
21 ratings
2 stars
19 ratings
1 star
25 ratings

SJ

Jun 12, 2018

Excellent course! Quiz questions are conceptual and challenging and assignments are pretty rigorous and 100% practical application oriented.

RR

Apr 19, 2019

Don't just read what's written on the projector. Try explaining it. And explain with code.

从本节课中

Object detection

In this week, we focus on the object detection task — one of the central problems in vision. We start with recalling the conventional sliding window + classifier approach culminating in Viola-Jones detector. Tracing the development of deep convolutional detectors up until recent days, we consider R-CNN and single shot detector models. Practice includes training a face detection model using a deep convolutional neural network.

Region-based convolutional neural network3:07

From R-CNN to Fast R-CNN5:09

Faster R-CNN4:28

Region-based fully-convolutional network2:18

Single shot detectors3:36

Speed vs. accuracy tradeoff1:59

Fun with pedestrian detectors1:20

教学方

Anton Konushin
Senior Lecturer
Alexey Artemov
Senior Lecturer

脚本

[SOUND] Faster R-CNN is the next step in evolution of R-CNN model. Essentially, Faster R-CNN is Fast R-CNN plus Regional Proposal Network. In Faster R-CNN, the last main problem of R-CNN approach is solved. The dependency from the external hypothesis generation method is removed. Objects are detected in a single pass with a single neural network. RPN is a simple fully convolutional network which is trained to its multitask class, similar to Fast R-CNN, and serves as a proposal generator. Experiments in neural network visualisation have shown that by decoding one response at a single pixel we can still roughly see the object outline. So finer localization information has been encoded in the channels of convolutional feature response. We can extract this information from localization objects with RPN. The Region Proposal Network is a small network that is slided over convolutional feature map. This small network takes its imput and then by N special window usually N equals 3. RPN simultaneously classify corresponding region as object unknown object in the regress bounding box location. Position of the sliding window provides localization information with reference to the image. Box regression provides finer localization with the reference to this sliding window itself. At each sliding window position a set of object proposals is defined. Each proposal has different size and aspect ratio. Such proposals are called anchors. Anchors improve handling of objects of different size and aspect ratio. Essentially anchors is a variant of sliding window with different sizes and aspect ratio. When training of Region Proposal Network anchor is marked as qualitative example if intersection over union is larger than 0.7, or it reaches maximum for all anchors for this particular ground truth example. Anchor is marked as negative sample if IoU is lower than 0.3. The box regression is straight, so to regress the box of positive examples to ground truth box, for the image with a resolution 1000 per 600 pixels and VGG-16 base architecture as feature extractor, they have 60 by 40 sliding window position and 9 anchors through each window position. So in total we have 21,500 proposals per image. Faster R-CNN can be trained end to end as one network with four losses. RPN classification loss, RPN regression loss, Fast R-CNN classification loss over classes, Fast R-CNN regression loss to regress the proposal bounding box, so the ground tools bounding box. We can easily change the Baesian architecture for feature extraction, and retrain Faster R-CNN model. For example, changing from VGG-16 to ResNet-101 model will give us 28% relative gain on Microsoft COCO dataset. By removing the dependency on external proposal generation method, speed is significantly improved, so Faster R-CNN, this VGG-based architecture can perform detection at five frames per second. Here are just an example of Faster R-CNN detection with ResNet-based architecture. You can see how many objects are detected. However, despite the anchor boxes, it can be difficult for RPN to handle objects of very different scales. RPN has fixed receptive field. So small objects can occupy a very small portion of receptive field or if objects are very large then the receptive field will contain only a part of the object. We can solve this problem by training a set of RPN for various scales. Each RPN will take different convolutional layer or set of layers as input so the receptive field will be of different size. This will significantly improve detection of small and large objects so one, Faster-RCN model can detect simultaneously objects from small to large sizes. [SOUND]

探索我们的目录

免费加入并获得个性化推荐、更新和优惠。

Coursera

关于
管理团队
工作机会
目录
证书
MasterTrack™ 证书
学位
企业版
政府版
面向校园

社区

学生
合作伙伴
开发者
Beta 测试人员
专业译员
博客
技术博客

更多

条款
隐私
帮助
内容访问
媒体
联系我们
目录
附属公司

随时随地学习

关注我们

© 2020 Coursera Inc.保留所有权利。