TY  - CONF
AU  - Bojana Gajic
AU  - Eduard Vazquez
AU  - Ramon Baldrich
A2  - VISIGRAPP
PY  - 2017//
TI  - Evaluation of Deep Image Descriptors for Texture Retrieval
BT  - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017)
SP  - 251
EP  - 257
KW  - Texture Representation
KW  - Texture Retrieval
KW  - Convolutional Neural Networks
KW  - Psychophysical Evaluation
N2  - 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.
UR  - https://pdfs.semanticscholar.org/0fb8/e49739fb3f9efd73033466af5428c59b1a3f.pdf
N1  - CIC; 600.087
ID  - Bojana Gajic2017
ER  -