Convolutional Neural Network Ensemble Fine-Tuning for Extended Transfer Learning

Oxana Korzh, Mikel Joaristi, Edoardo Serra

Research output: Chapter in Book/Report/Conference proceedingChapter

20 Scopus citations

Abstract

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%.

Original languageAmerican English
Title of host publicationBigData 2018
EditorsLatifur Khan, Liang-Jie Zhang, Kisung Lee, Francis Y. Chin, C. L. Chen
PublisherSpringer Verlag
Pages110-123
Number of pages14
ISBN (Print)9783319943008
DOIs
StatePublished - 1 Jan 2018
Event7th International Congress on Big Data, BigData 2018 Held as Part of the Services Conference Federation, SCF 2018 - Seattle, United States
Duration: 25 Jun 201830 Jun 2018

Publication series

Name0302-9743

Conference

Conference7th International Congress on Big Data, BigData 2018 Held as Part of the Services Conference Federation, SCF 2018
Country/TerritoryUnited States
CitySeattle
Period25/06/1830/06/18

Keywords

  • CNN
  • deep learning
  • image classification
  • transfer learning

EGS Disciplines

  • Computer Sciences

Fingerprint

Dive into the research topics of 'Convolutional Neural Network Ensemble Fine-Tuning for Extended Transfer Learning'. Together they form a unique fingerprint.

Cite this