ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks

With event-driven algorithms, especially spiking neural networks (SNNs), achieving continuous improvement in neuromorphic vision processing, a more challenging event-stream dataset is urgently needed. However, it is well-known that creating an ES-dataset is a time-consuming and costly task with neur...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yihan Lin, Wei Ding, Shaohua Qiang, Lei Deng, Guoqi Li
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	data set spiking neural network dynamic vision sensor brain inspire computation leaky integrate and fire Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/2161847bfb6d4587a5ff385bf40c39d2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2161847bfb6d4587a5ff385bf40c39d2
record_format	dspace
spelling	oai:doaj.org-article:2161847bfb6d4587a5ff385bf40c39d22021-11-30T23:39:10ZES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks1662-453X10.3389/fnins.2021.726582https://doaj.org/article/2161847bfb6d4587a5ff385bf40c39d22021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fnins.2021.726582/fullhttps://doaj.org/toc/1662-453XWith event-driven algorithms, especially spiking neural networks (SNNs), achieving continuous improvement in neuromorphic vision processing, a more challenging event-stream dataset is urgently needed. However, it is well-known that creating an ES-dataset is a time-consuming and costly task with neuromorphic cameras like dynamic vision sensors (DVS). In this work, we propose a fast and effective algorithm termed Omnidirectional Discrete Gradient (ODG) to convert the popular computer vision dataset ILSVRC2012 into its event-stream (ES) version, generating about 1,300,000 frame-based images into ES-samples in 1,000 categories. In this way, we propose an ES-dataset called ES-ImageNet, which is dozens of times larger than other neuromorphic classification datasets at present and completely generated by the software. The ODG algorithm implements image motion to generate local value changes with discrete gradient information in different directions, providing a low-cost and high-speed method for converting frame-based images into event streams, along with Edge-Integral to reconstruct the high-quality images from event streams. Furthermore, we analyze the statistics of ES-ImageNet in multiple ways, and a performance benchmark of the dataset is also provided using both famous deep neural network algorithms and spiking neural network algorithms. We believe that this work shall provide a new large-scale benchmark dataset for SNNs and neuromorphic vision.Yihan LinWei DingShaohua QiangLei DengGuoqi LiFrontiers Media S.A.articledata setspiking neural networkdynamic vision sensorbrain inspire computationleaky integrate and fireNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Neuroscience, Vol 15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	data set spiking neural network dynamic vision sensor brain inspire computation leaky integrate and fire Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	data set spiking neural network dynamic vision sensor brain inspire computation leaky integrate and fire Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Yihan Lin Wei Ding Shaohua Qiang Lei Deng Guoqi Li ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
description	With event-driven algorithms, especially spiking neural networks (SNNs), achieving continuous improvement in neuromorphic vision processing, a more challenging event-stream dataset is urgently needed. However, it is well-known that creating an ES-dataset is a time-consuming and costly task with neuromorphic cameras like dynamic vision sensors (DVS). In this work, we propose a fast and effective algorithm termed Omnidirectional Discrete Gradient (ODG) to convert the popular computer vision dataset ILSVRC2012 into its event-stream (ES) version, generating about 1,300,000 frame-based images into ES-samples in 1,000 categories. In this way, we propose an ES-dataset called ES-ImageNet, which is dozens of times larger than other neuromorphic classification datasets at present and completely generated by the software. The ODG algorithm implements image motion to generate local value changes with discrete gradient information in different directions, providing a low-cost and high-speed method for converting frame-based images into event streams, along with Edge-Integral to reconstruct the high-quality images from event streams. Furthermore, we analyze the statistics of ES-ImageNet in multiple ways, and a performance benchmark of the dataset is also provided using both famous deep neural network algorithms and spiking neural network algorithms. We believe that this work shall provide a new large-scale benchmark dataset for SNNs and neuromorphic vision.
format	article
author	Yihan Lin Wei Ding Shaohua Qiang Lei Deng Guoqi Li
author_facet	Yihan Lin Wei Ding Shaohua Qiang Lei Deng Guoqi Li
author_sort	Yihan Lin
title	ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
title_short	ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
title_full	ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
title_fullStr	ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
title_full_unstemmed	ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
title_sort	es-imagenet: a million event-stream classification dataset for spiking neural networks
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/2161847bfb6d4587a5ff385bf40c39d2
work_keys_str_mv	AT yihanlin esimagenetamillioneventstreamclassificationdatasetforspikingneuralnetworks AT weiding esimagenetamillioneventstreamclassificationdatasetforspikingneuralnetworks AT shaohuaqiang esimagenetamillioneventstreamclassificationdatasetforspikingneuralnetworks AT leideng esimagenetamillioneventstreamclassificationdatasetforspikingneuralnetworks AT guoqili esimagenetamillioneventstreamclassificationdatasetforspikingneuralnetworks
_version_	1718406188779962368

ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks

Ejemplares similares