一区论文
来源:互联网 发布:镆铪合金知乎 编辑:程序博客网 时间:2024/05/09 23:27
《Automatic land cover classification of geo-tagged fieldphotos by deep learning》
ABSTRACT
1.Introduction
Global land covermapping→photographs→field photo collecting及几个图形库 +深度学习
2. Methodology
2.1. Transfer learning
迁移学习是什么:Transfer learning was proposed to apply a pre-trained neural networkto another related problem. A pre-trained neural network will include both itsmodel structure and the network weights trained with large datasets.
两种迁移学习模型修改方式: Fine-tuningmeans continuing training the pre-trained CNN model with another newdataset, according to the task of interest. This process will adjust thenetwork weights of the pre-trained model to fit its outputs as close to newlabels as possible.(“fine-tuning首先是一个类似MLP的结构,但是除了最后一层的权重和bias是随机初始化的之外,其余的权重是在pre-training中训练好的。用在什么地方都可以”)Featureextraction works by removing the last layer of aCNN model (output layer) and treating the output data of the second last layeras extracted features (also called CNN codes), which are always highdimensional vectors and implicitly represent characteristics of input images.The extracted features then can be analysed by otherclassifying models, such aslogistic regression,multinomial logistic regression orsupport vector machine. In feature extraction, thepre-trained CNN model acts as the image feature extractor in the wholeworkflow.
MLP(多层感知机)http://www.360doc.com/content/15/0414/14/12067640_463128216.shtml
(本实验选用feature extraction,∵the GlobalGeo-referenced Field Photo Library has only nearly 30,000 training samples forlandscape classification, whichmay cause overfitting ifthe CNN model is fine-tuned until the first layer)
(本实验选用Inception-v3、multinomial logistic regression model,removing the last output layer of the pre-trainedInception-v3 model, the image feature extractor wasthen acquired with the output of 2048 CNN codes (image features). The CNN codeswere then classified by a weighted multinomial logistic regression modelfor land cover type recognition)
2.2. Weighted multinomial logisticregression
网络最后一层多项逻辑回归分类器 softmax
(sigmoid函数只能分两类,而softmax能分多类,softmax是sigmoid的扩展)
模型训练的过程(其中,The process of model training is to find outthe best model parameter that minimises the difference between thepredicted and the actual probability that samples belong to each category.Thegradient descentmethod is used to search for optimum parameterθ, whichis an iterative algorithm thatupdates parameterθstep by step)
3. Experiment design
3.1. Data sources
3.2. Model training and validation
the labelled samples are divided into twosubsets: training and testing set……训练过程
a photo belongs to every land cover typesare given by the multinomial logistic regression. The type with the highestprobability will be taken as the predicted type within the photo
4.Experiment result
4.1. Overall accuracy
4.2. Predicted probability
4.3. User and produceraccuracy
5. Discussion
5.1. Model performance
5.2. Sample quality
6. Conclusions
本文贡献:This research is focused on proposing a new approach to applying thedeep learning for geographic and environmental studies. The main contributionis to prove the possibility that artificial intelligence can help with land coverclassification and to evaluate how well the model can perform .
Acknowledgements
References
- 一区论文
- 资源一 论文 计算机
- Latex论文排版( 一)
- 论文纠错(一)
- 论文阅读(一)
- 论文理解:AlexNet(一)
- 系统分析员论文样例(一)
- 论文阅读笔记(一)
- 论文写作技巧(一)
- 精彩论文摘抄(一)
- 论文笔记(一) GOTURN
- YOLO9000论文阅读笔记(一)
- SSD论文学习总结一
- [科研论文]W5100相关科研论文(一)
- VC++ 2008本科毕业学生论文指导一
- 论文一 企业人事信息系统的应用
- 求一 工作安排系统 论文
- 【LaTeX排版】LaTeX论文排版<一>
- 记录我的代码【01】租车系统
- 顺序表应用4:元素位置互换之逆置算法
- Ubuntu更新时提示错误 E: Sub-process /usr/bin/dpkg returned an error code (1)
- 第七章:Django开发中cookie与session的使用
- 用异或进行两个数交换的陷阱
- 一区论文
- 1005. Spell It Right (20)
- 2015年全国大学生电子设计竞赛 F题:数字频率计
- 记录我的代码【02】小日历
- 【HDU 6034】Balala Power!(贪心+进制转换)
- 前海征信“好信杯”大数据算法竞赛
- C++的三大特性——继承
- mysql 修改root密码
- [数学建模]线性规划与matlab解法