Learning channel-wise ordered aggregations in deep neural networks
| dc.contributor.author | Domínguez Catena, Iris | |
| dc.contributor.author | Paternain Dallo, Daniel | |
| dc.contributor.author | Galar Idoate, Mikel | |
| dc.contributor.department | Institute of Smart Cities - ISC | en |
| dc.contributor.funder | Universidad Pública de Navarra / Nafarroako Unibertsitate Publikoa | es |
| dc.date.accessioned | 2021-02-19T08:12:03Z | |
| dc.date.available | 2022-07-11T23:00:14Z | |
| dc.date.issued | 2021 | |
| dc.description | Trabajo presentado a la International Conference on Intelligent and Fuzzy Systems, INFUS 2020, 21-23 July 2020, Istanbul, Turkey | es |
| dc.description.abstract | One of the most common techniques for approaching image classification problems are Deep Neural Networks. These systems are capable of classifying images with different levels of detail at different levels of detail, with an accuracy that sometimes can surpass even manual classification by humans. Most common architectures for Deep Neural Networks are based on convolutional layers, which perform at the same time a convolution on each input channel and a linear aggregation on the convoluted channels. In this work, we develop a new method for augmenting the information of a layer inside a Deep Neural Network using channel-wise ordered aggregations. We develop a new layer that can be placed at different points inside a Deep Neural Network. This layer takes the feature maps of the previous layer and adds new feature maps by applying several channel-wise ordered aggregations based on learned weighting vectors. We perform several experiments introducing this layer in a VGG neural network and study the impact of the new layer, obtaining better accuracy scores over a sample dataset based on ImageNet. We also study the convergence and evolution of the weighting vectors of the new layers over the learning process, which gives a better understanding of the way the system is exploiting the additional information to gain new knowledge. | en |
| dc.description.sponsorship | This work was partially supported by the Public University of Navarre under the projects PJUPNA13 and PJUPNA1926. | en |
| dc.embargo.lift | 2022-07-11 | |
| dc.embargo.terms | 2022-07-11 | |
| dc.format.extent | 8 p. | |
| dc.format.mimetype | application/pdf | en |
| dc.identifier.doi | 10.1007/978-3-030-51156-2_119 | |
| dc.identifier.isbn | 978-3-030-51156-2 (Electronic) | |
| dc.identifier.uri | https://academica-e.unavarra.es/handle/2454/39252 | |
| dc.language.iso | eng | en |
| dc.publisher | Springer | en |
| dc.relation.ispartof | Kahraman C., Cevik Onar S., Oztaysi B., Sari I., Cebi S., Tolga A. (eds) Intelligent and Fuzzy Techniques: Smart and Innovative Solutions. INFUS 2020. Advances in Intelligent Systems and Computing, vol 1197. Springer, Cham, 2021, pp. 1023-1030. ISBN 978-3-030-51156-2 | en |
| dc.relation.publisherversion | https://doi.org/10.1007/978-3-030-51156-2_119 | |
| dc.rights | © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021. | en |
| dc.rights.accessRights | info:eu-repo/semantics/openAccess | |
| dc.subject | Neural nets | en |
| dc.subject | RNN | en |
| dc.subject | Deep Learning | en |
| dc.subject | Ordered aggregations | en |
| dc.title | Learning channel-wise ordered aggregations in deep neural networks | en |
| dc.type | info:eu-repo/semantics/conferenceObject | |
| dc.type.version | info:eu-repo/semantics/acceptedVersion | |
| dspace.entity.type | Publication | |
| relation.isAuthorOfPublication | 2ba22a83-13df-4d11-8e44-f9e97dbc13d0 | |
| relation.isAuthorOfPublication | ca16c024-51e4-4f8f-b457-dc5307be32d9 | |
| relation.isAuthorOfPublication | 44c7a308-9c21-49ef-aa03-b45c2c5a06fd | |
| relation.isAuthorOfPublication.latestForDiscovery | 2ba22a83-13df-4d11-8e44-f9e97dbc13d0 |