Authors:
Bojana Gajic
1
;
Eduard Vazquez
2
and
Ramon Baldrich
1
Affiliations:
1
Universitat Autonoma de Barcelona, Spain
;
2
Cortexica Vision Systems, United Kingdom
Keyword(s):
Texture Representation, Texture Retrieval, Convolutional Neural Networks, Psychophysical Evaluation.
Related
Ontology
Subjects/Areas/Topics:
Color and Texture Analyses
;
Computer Vision, Visualization and Computer Graphics
;
Image and Video Analysis
Abstract:
The increasing complexity learnt in the layers of a Convolutional Neural Network has proven to be of great
help for the task of classification. The topic has received great attention in recently published literature.
Nonetheless, just a handful of works study low-level representations, commonly associated with lower layers.
In this paper, we explore recent findings which conclude, counterintuitively, the last layer of the VGG
convolutional network is the best to describe a low-level property such as texture. To shed some light on this
issue, we are proposing a psychophysical experiment to evaluate the adequacy of different layers of the VGG
network for texture retrieval. Results obtained suggest that, whereas the last convolutional layer is a good
choice for a specific task of classification, it might not be the best choice as a texture descriptor, showing a
very poor performance on texture retrieval. Intermediate layers show the best performance, showing a good
combination of basic
filters, as in the primary visual cortex, and also a degree of higher level information to
describe more complex textures.
(More)