Ponencia
A preliminary study on deep transfer learning applied to image classification for small datasets
Autor/es | Molina, Miguel Ángel
Asencio Cortés, Gualberto Riquelme Santos, José Cristóbal Martínez Álvarez, Francisco |
Departamento | Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos |
Fecha de publicación | 2020 |
Fecha de depósito | 2023-05-02 |
Publicado en |
|
ISBN/ISSN | 978-3-030-57801-5 (impreso) 978-3-030-57802-2 (online) |
Resumen | A new transfer learning strategy is proposed for image classification in this work, based on an 8-layer convolutional neural network. The transfer learning process consists in a training phase of the neural network on a ... A new transfer learning strategy is proposed for image classification in this work, based on an 8-layer convolutional neural network. The transfer learning process consists in a training phase of the neural network on a source dataset of images. Then, the last two layers are retrained using a different small target dataset of images. A preliminary study was conducted to train and test the transfer learning proposal on Malaria cell images for a binary classification problem. The methodology proposed has provided a 6.76% of improvement with respect to other three different strategies of training non-transfer learning models. The results achieved are quite promising and encourage to conduct further research in this field. |
Agencias financiadoras | Ministerio de Economía y Competitividad (MINECO). España |
Identificador del proyecto | TIN2017-88209-C2-1-R |
Cita | Molina, M.Á., Asencio Cortés, G., Riquelme Santos, J.C. y Martínez Álvarez, F. (2020). A preliminary study on deep transfer learning applied to image classification for small datasets. En SOCO 2020: 15th International Conference on Soft Computing Models in Industrial and Environmental Applications (741-750), Burgos, España: Springer. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
A preliminary study on deep ... | 337.9Kb | [PDF] | Ver/ | |