Transfer Learning for Illustration Classification

Lagunas, Manuel; Garces, Elena

Transfer Learning for Illustration Classification

Files

077-085.pdf (13.7 MB)

Date

2017

Authors

Lagunas, Manuel
Garces, Elena

Publisher

The Eurographics Association

Abstract

The field of image classification has shown an outstanding success thanks to the development of deep learning techniques. Despite the great performance obtained, most of the work has focused on natural images ignoring other domains like artistic depictions. In this paper, we use transfer learning techniques to propose a new classification network with better performance in illustration images. Starting from the deep convolutional network VGG19, pre-trained with natural images, we propose two novel models which learn object representations in the new domain. Our optimized network will learn new low-level features of the images (colours, edges, textures) while keeping the knowledge of the objects and shapes that it already learned from the ImageNet dataset. Thus, requiring much less data for the training. We propose a novel dataset of illustration images labelled by content where our optimized architecture achieves 86.61% of top-1 and 97.21% of top-5 precision. We additionally demonstrate that our model is still able to recognize objects in photographs.

        @inproceedings{10.2312:ceig.20171213
,
booktitle = {Spanish Computer Graphics Conference (CEIG)
},
editor = {Fco. Javier Melero and Nuria Pelechano
},
title = {{Transfer Learning for Illustration Classification
}},
author = {Lagunas, Manuel and 
Garces, Elena
},
year = {2017
},
publisher = {The Eurographics Association
},
ISSN = {-
},
ISBN = {978-3-03868-046-8
},
DOI = {10.2312/ceig.20171213
}
}