Title:
|
On the representativeness of convolutional neural networks layers
|
Author:
|
García Gasulla, Darío; Moreno, Jonatan; Ramos-Pollan, Raúl; Casadiegos Barrios, Romel; Béjar Alonso, Javier; Cortés García, Claudio Ulises; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José; Suzumura, Toyotaro
|
Other authors:
|
Universitat Politècnica de Catalunya. Departament de Ciències de la Computació; Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors; Universitat Politècnica de Catalunya. KEMLG - Grup d'Enginyeria del Coneixement i Aprenentatge Automàtic; Universitat Politècnica de Catalunya. CAP - Grup de Computació d'Altes Prestacions |
Abstract:
|
Convolutional Neural Networks (CNN) are the most popular of deep network models due to their applicability and success in image processing. Although plenty of effort has been made in designing and training better discriminative CNNs, little is yet known about the internal features these models learn. Questions like, what specific knowledge is coded within CNN layers, and how can it be used for other purposes besides discrimination, remain to be answered. To advance in the resolution of these questions, in this work we extract features from CNN layers, building vector representations from CNN activations. The resultant vector embedding is used to represent first images and then known image classes. On those representations we perform an unsupervised clustering process, with the goal of studying the hidden semantics captured in the embedding space. Several abstract entities untaught to the network emerge in this process, effectively defining a taxonomy of knowledge as perceived by the CNN. We evaluate and interpret these sets using WordNet, while studying the different behaviours exhibited by the layers of a CNN model according to their depth. Our results indicate that, while top (i.e., deeper) layers provide the most representative space, low layers also define descriptive dimensions. |
Abstract:
|
This work was partially supported by the IBM/BSC Technology Center for Supercomputing (Joint Study Agreement, No. W156463), by the Spanish Government through Programa Severo Ochoa (SEV-2015-0493), by the Spanish Ministry of Science and Technology through TIN2015-65316-P project and by the Generalitat de Catalunya (contracts
2014-SGR-1051). |
Abstract:
|
Peer Reviewed |
Subject(s):
|
-Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial -Neural networks (Computer science) -Image processing -Convolutional neural networks -Visual embeddings -Unsupervised learning -Xarxes neuronals (Informàtica) -Imatges -- Processament |
Rights:
|
|
Document type:
|
Article - Submitted version Book Part |
Published by:
|
IOS PRESS EBOOKS
|
Share:
|
|