Reducing Latency in a Converted Spiking Video Segmentation Network
METADATA ONLY
Author / Producer
Date
2021
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
Spiking Neural Networks (SNNs) can be configured to produce almost-equivalent accurate Analog Neural Networks (ANNs) by various ANN-SNN conversion methods. Most of these methods are applied to classification and object detection networks tested on frame-based datasets. In this work, we demonstrate a converted SNN for image segmentation and applied to a natural video dataset. Instead of resetting the network state with each input frame, we capitalize on the temporal redundancy between adjacent frames in a natural scene, and propose an interval reset method where the network state is reset after a fixed number of frames. We studied the trade-off between accuracy and latency with the number of interval reset frames. We also applied layer-specific normalization and early stopping to speed up network convergence and to reduce the latency. Our results show that the SNN achieved a 35.7x increase in convergence speed with only 1.5% accuracy drop using an interval reset of 20 frames. © 2021 IEEE
Permanent link
Publication status
published
Editor
Book title
2021 IEEE International Symposium on Circuits and Systems (ISCAS)
Journal / series
Volume
Pages / Article No.
9401667
Publisher
IEEE
Event
IEEE International Symposium on Circuits and Systems (ISCAS 2021)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
image segmentation; spiking neural network; ANN-SNN conversion
Organisational unit
08836 - Delbrück, Tobias (Tit.-Prof.)