Deep Spiking Convolutional Neural Network ...
Type de document :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
Titre :
Deep Spiking Convolutional Neural Network for Single Object Localization Based On Deep Continuous Local Learning
Auteur(s) :
Barchid, Sami [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Mennesson, José [Auteur]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Centre for Digital Systems [CERI SN - IMT Nord Europe]
Djeraba, Chaabane [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Mennesson, José [Auteur]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Centre for Digital Systems [CERI SN - IMT Nord Europe]
Djeraba, Chaabane [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Titre de la manifestation scientifique :
CBMI 2021 - Content-based Multimedia Indexing
Ville :
Lille / Virtual
Pays :
France
Date de début de la manifestation scientifique :
2021-06-28
Mot(s)-clé(s) en anglais :
Deep Spiking Neural Network
SNN
Convolution
Object Localization
SNN
Convolution
Object Localization
Discipline(s) HAL :
Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
Résumé en anglais : [en]
With the advent of neuromorphic hardware, spiking neural networks can be a good energy-efficient alternative to artificial neural networks. However, the use of spiking neural networks to perform computer vision tasks remains ...
Lire la suite >With the advent of neuromorphic hardware, spiking neural networks can be a good energy-efficient alternative to artificial neural networks. However, the use of spiking neural networks to perform computer vision tasks remains limited, mainly focusing on simple tasks such as digit recognition. It remains hard to deal with more complex tasks (e.g. segmentation, object detection) due to the small number of works on deep spiking neural networks for these tasks. The objective of this paper is to make the first step towards modern computer vision with supervised spiking neural networks. We propose a deep convolutional spiking neural network for the localization of a single object in a grayscale image. We propose a network based on DECOLLE, a spiking model that enables local surrogate gradient-based learning. The encouraging results reported on Oxford-IIIT-Pet validates the exploitation of spiking neural networks with a supervised learning approach for more elaborate vision tasks in the future.Lire moins >
Lire la suite >With the advent of neuromorphic hardware, spiking neural networks can be a good energy-efficient alternative to artificial neural networks. However, the use of spiking neural networks to perform computer vision tasks remains limited, mainly focusing on simple tasks such as digit recognition. It remains hard to deal with more complex tasks (e.g. segmentation, object detection) due to the small number of works on deep spiking neural networks for these tasks. The objective of this paper is to make the first step towards modern computer vision with supervised spiking neural networks. We propose a deep convolutional spiking neural network for the localization of a single object in a grayscale image. We propose a network based on DECOLLE, a spiking model that enables local surrogate gradient-based learning. The encouraging results reported on Oxford-IIIT-Pet validates the exploitation of spiking neural networks with a supervised learning approach for more elaborate vision tasks in the future.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- https://hal.archives-ouvertes.fr/hal-03264038/document
- Accès libre
- Accéder au document
- http://arxiv.org/pdf/2105.05609
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-03264038/document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-03264038/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- CBMI_2021___FPN_Decolle%281%29.pdf
- Accès libre
- Accéder au document
- 2105.05609
- Accès libre
- Accéder au document