首页> 外文会议>Big data - BigData 2018 >Convolutional Neural Network Ensemble Fine-Tuning for Extended Transfer Learning

【24h】

Convolutional Neural Network Ensemble Fine-Tuning for Extended Transfer Learning

机译：卷积神经网络集成微调用于扩展转移学习

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Nowadays, image classification is a core task for many high impact applications such as object recognition, self-driving cars, national security (border monitoring, assault detection), safety (fire detection, distracted driving), geo-monitoring (cloud, rock and crop-disease detection). Convolutional Neural Networks(CNNs) are effective for those applications. However, they need to be trained with a huge number of examples and a consequently huge training time. Unfortunately, when the training set is not big enough and when re-train the model several times is needed, a common approach is to adopt a transfer learning procedure. Transfer learning procedures use networks already pretrained in other context and extract features from them or retrain them with a small dataset related to the specific application (fine-tuning). We propose to fine-tuning an ensemble of models combined together from multiple pretrained CNNs (AlexNet, VGG19 and GoogleNet). We test our approach on three different benchmark datasets: Yahoo! Shopping Shoe Image Content, UC Merced Land Use Dataset, and Caltech-UCSD Birds-200-2011 Dataset. Each one represents a different application. Our suggested approach always improves accuracy over the state of the art solutions and accuracy obtained by the returning of a single CNN. In the best case, we moved from accuracy of 70.5% to 93.14%.

机译：如今，图像分类已成为许多高影响力应用程序的核心任务，例如对象识别，自动驾驶汽车，国家安全（边界监视，攻击检测），安全（火灾检测，分心驾驶），地理监视（云，岩石和岩石）。作物疾病检测）。卷积神经网络（CNN）对于那些应用是有效的。但是，他们需要通过大量示例进行培训，从而需要大量的培训时间。不幸的是，当训练集不够大并且需要对模型进行多次训练时，一种常见的方法是采用转移学习过程。转移学习程序使用已经在其他环境中进行过预训练的网络，并从中提取特征或使用与特定应用程序相关的小型数据集对它们进行重新训练（微调）。我们建议微调来自多个预训练的CNN（AlexNet，VGG19和GoogleNet）的模型集合。我们在三种不同的基准数据集上测试了我们的方法：Yahoo!购物鞋图片内容，UC Merced土地使用数据集和Caltech-UCSD Birds-200-2011数据集。每个代表一个不同的应用程序。我们建议的方法始终可以提高现有解决方案的准确性，并可以通过返回单个CNN来提高准确性。在最好的情况下，我们从70.5％的准确性提高到93.14％。

著录项

来源
《Big data - BigData 2018》|2018年|110-123|共14页
会议地点 Seattle(US)
作者
Oxana Korzh; Mikel Joaristi; Edoardo Serra;
展开▼
作者单位

Computer Science Department, Boise State University, Boise, USA;

Computer Science Department, Boise State University, Boise, USA;

Computer Science Department, Boise State University, Boise, USA;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
Image classification; CNN; Deep learning; Transfer learning;

机译：图像分类； CNN;深度学习；转移学习;

相似文献

外文文献
中文文献
专利

1. Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries [J] . Applied Energy . 2020,第Feba15期

机译：具有集成学习和传递学习的深度卷积神经网络，用于锂离子电池的容量估计
2. Fine-tuning convolutional neural network with transfer learning for semantic segmentation of ground-level oilseed rape images in a field with high weed pressure [J] . Abdalla Alwaseela, Cen Haiyan, Wan Liang, Computers and Electronics in Agriculture . 2019,第期

机译：具有高杂草压力的田间地下油菜图像地面油菜图像语义分割的微调卷积神经网络
3. Estimating Body Condition Score in Dairy Cows From Depth Images Using Convolutional Neural Networks, Transfer Learning and Model Ensembling Techniques [J] . Juan Rodríguez Alvarez, Mauricio Arroqui, Pablo Mangudo, Agronomy . 2019,第2期

机译：使用卷积神经网络，转移学习和模型集成技术从深度图像估算奶牛的身体状况得分
4. Convolutional Neural Network Ensemble Fine-Tuning for Extended Transfer Learning [C] . Oxana Korzh, Mikel Joaristi, Edoardo Serra International Congress on Big Data . 2018

机译：卷积神经网络集合微调扩展转移学习
5. Plant Segmentation by Supervised Machine Learning Methods and Phenotypic Trait Extraction of Soybean Plants Using Deep Convolutional Neural Networks with Transfer Learning [D] . Adams, Jason R. 2020

机译：植物分割通过深度卷积神经网络与转移学习的豆豆植物的植物分割和表型特性
6. Early Detection of Alzheimer’s Disease Using Magnetic Resonance Imaging: A Novel Approach Combining Convolutional Neural Networks and Ensemble Learning [O] . Dan Pan, An Zeng, Longfei Jia, 2020

机译：利用磁共振成像早期检测阿尔茨海默病：一种新的方法结合卷积神经网络和集合学习
7. Convolutional Neural Networks: Ensemble Modeling, Fine-Tuning and Unsupervised Semantic Localization for Intraoperative CLE Images [O] . Izadyyazdanabadi, Mohammadhassan, Belykh, Evgenii, Mooney, Michael, 2017

机译：卷积神经网络：集合建模，微调和术中CLE图像的无监督语义定位

Convolutional Neural Network Ensemble Fine-Tuning for Extended Transfer Learning

摘要

著录项

相似文献

相关主题

期刊订阅