Improving Transfer Learning Performance: An Application in the Classification of Remote Sensing Data

Gabriel Tenorio, Cristian Villalobos, Leonardo Mendoza, Eduardo Costa da Silva, Wouter Caarls

2019

Abstract

The present paper aims to train and analyze Convolutional Neural Networks (CNN or ConvNets) capable of classifying plant species of a certain region for applications in an environmental monitoring system. In order to achieve this for a limited training dataset, the samples were expanded with the use of a data generator algorithm. Next, transfer learning and fine tuning methods were applied with pre-trained networks. With the purpose of choosing the best layers to be transferred, a statistical dispersion method was proposed. Through a distributed training method, the training speed and performance for the CNN in CPUs was improved. After tuning the parameters of interest in the resulting network by the cross-validation method, the learning capacity of the network was verified. The obtained results indicate an accuracy of about 97%, which was acquired transferring the pre-trained first seven convolutional layers of the VGG-16 network to a new sixteen-layer convolutional network in which the final training was performed. This represents an improvement over the state of the art, which had an accuracy of 91% on the same dataset.

Download


Paper Citation


in Harvard Style

Tenorio G., Villalobos C., Mendoza L., Costa da Silva E. and Caarls W. (2019). Improving Transfer Learning Performance: An Application in the Classification of Remote Sensing Data.In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-350-6, pages 174-183. DOI: 10.5220/0007372201740183


in Bibtex Style

@conference{icaart19,
author={Gabriel Tenorio and Cristian Villalobos and Leonardo Mendoza and Eduardo Costa da Silva and Wouter Caarls},
title={Improving Transfer Learning Performance: An Application in the Classification of Remote Sensing Data},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2019},
pages={174-183},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007372201740183},
isbn={978-989-758-350-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Improving Transfer Learning Performance: An Application in the Classification of Remote Sensing Data
SN - 978-989-758-350-6
AU - Tenorio G.
AU - Villalobos C.
AU - Mendoza L.
AU - Costa da Silva E.
AU - Caarls W.
PY - 2019
SP - 174
EP - 183
DO - 10.5220/0007372201740183