Spiking Two-Stream Methods with Unsupervised STDP-based Learning for Action Recognition

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: El-Assal, Mireille, Tirilly, Pierre, Bilasco, Ioan Marius
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917908837302272
author El-Assal, Mireille
Tirilly, Pierre
Bilasco, Ioan Marius
author_facet El-Assal, Mireille
Tirilly, Pierre
Bilasco, Ioan Marius
contents Video analysis is a computer vision task that is useful for many applications like surveillance, human-machine interaction, and autonomous vehicles. Deep Convolutional Neural Networks (CNNs) are currently the state-of-the-art methods for video analysis. However they have high computational costs, and need a large amount of labeled data for training. In this paper, we use Convolutional Spiking Neural Networks (CSNNs) trained with the unsupervised Spike Timing-Dependent Plasticity (STDP) learning rule for action classification. These networks represent the information using asynchronous low-energy spikes. This allows the network to be more energy efficient and neuromorphic hardware-friendly. However, the behaviour of CSNNs is not studied enough with spatio-temporal computer vision models. Therefore, we explore transposing two-stream neural networks into the spiking domain. Implementing this model with unsupervised STDP-based CSNNs allows us to further study the performance of these networks with video analysis. In this work, we show that two-stream CSNNs can successfully extract spatio-temporal information from videos despite using limited training data, and that the spiking spatial and temporal streams are complementary. We also show that using a spatio-temporal stream within a spiking STDP-based two-stream architecture leads to information redundancy and does not improve the performance.
format Preprint
id arxiv_https___arxiv_org_abs_2306_13783
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Spiking Two-Stream Methods with Unsupervised STDP-based Learning for Action Recognition
El-Assal, Mireille
Tirilly, Pierre
Bilasco, Ioan Marius
Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
Video analysis is a computer vision task that is useful for many applications like surveillance, human-machine interaction, and autonomous vehicles. Deep Convolutional Neural Networks (CNNs) are currently the state-of-the-art methods for video analysis. However they have high computational costs, and need a large amount of labeled data for training. In this paper, we use Convolutional Spiking Neural Networks (CSNNs) trained with the unsupervised Spike Timing-Dependent Plasticity (STDP) learning rule for action classification. These networks represent the information using asynchronous low-energy spikes. This allows the network to be more energy efficient and neuromorphic hardware-friendly. However, the behaviour of CSNNs is not studied enough with spatio-temporal computer vision models. Therefore, we explore transposing two-stream neural networks into the spiking domain. Implementing this model with unsupervised STDP-based CSNNs allows us to further study the performance of these networks with video analysis. In this work, we show that two-stream CSNNs can successfully extract spatio-temporal information from videos despite using limited training data, and that the spiking spatial and temporal streams are complementary. We also show that using a spatio-temporal stream within a spiking STDP-based two-stream architecture leads to information redundancy and does not improve the performance.
title Spiking Two-Stream Methods with Unsupervised STDP-based Learning for Action Recognition
topic Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
url https://arxiv.org/abs/2306.13783