Event-based Optical Flow on Neuromorphic Processor: ANN vs. SNN Comparison based on Activation Sparsification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Yingfu, Tang, Guangzhi, Yousefzadeh, Amirreza, de Croon, Guido, Sifalakis, Manolis
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910546054348800
author Xu, Yingfu
Tang, Guangzhi
Yousefzadeh, Amirreza
de Croon, Guido
Sifalakis, Manolis
author_facet Xu, Yingfu
Tang, Guangzhi
Yousefzadeh, Amirreza
de Croon, Guido
Sifalakis, Manolis
contents Spiking neural networks (SNNs) for event-based optical flow are claimed to be computationally more efficient than their artificial neural networks (ANNs) counterparts, but a fair comparison is missing in the literature. In this work, we propose an event-based optical flow solution based on activation sparsification and a neuromorphic processor, SENECA. SENECA has an event-driven processing mechanism that can exploit the sparsity in ANN activations and SNN spikes to accelerate the inference of both types of neural networks. The ANN and the SNN for comparison have similar low activation/spike density (~5%) thanks to our novel sparsification-aware training. In the hardware-in-loop experiments designed to deduce the average time and energy consumption, the SNN consumes 44.9ms and 927.0 microjoules, which are 62.5% and 75.2% of the ANN's consumption, respectively. We find that SNN's higher efficiency attributes to its lower pixel-wise spike density (43.5% vs. 66.5%) that requires fewer memory access operations for neuron states.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20421
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Event-based Optical Flow on Neuromorphic Processor: ANN vs. SNN Comparison based on Activation Sparsification
Xu, Yingfu
Tang, Guangzhi
Yousefzadeh, Amirreza
de Croon, Guido
Sifalakis, Manolis
Neural and Evolutionary Computing
Computer Vision and Pattern Recognition
Machine Learning
Spiking neural networks (SNNs) for event-based optical flow are claimed to be computationally more efficient than their artificial neural networks (ANNs) counterparts, but a fair comparison is missing in the literature. In this work, we propose an event-based optical flow solution based on activation sparsification and a neuromorphic processor, SENECA. SENECA has an event-driven processing mechanism that can exploit the sparsity in ANN activations and SNN spikes to accelerate the inference of both types of neural networks. The ANN and the SNN for comparison have similar low activation/spike density (~5%) thanks to our novel sparsification-aware training. In the hardware-in-loop experiments designed to deduce the average time and energy consumption, the SNN consumes 44.9ms and 927.0 microjoules, which are 62.5% and 75.2% of the ANN's consumption, respectively. We find that SNN's higher efficiency attributes to its lower pixel-wise spike density (43.5% vs. 66.5%) that requires fewer memory access operations for neuron states.
title Event-based Optical Flow on Neuromorphic Processor: ANN vs. SNN Comparison based on Activation Sparsification
topic Neural and Evolutionary Computing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2407.20421