ViT-LCA: A Neuromorphic Approach for Vision Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Takaghaj, Sanaz Mahmoodi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910910166073344
author Takaghaj, Sanaz Mahmoodi
author_facet Takaghaj, Sanaz Mahmoodi
contents The recent success of Vision Transformers has generated significant interest in attention mechanisms and transformer architectures. Although existing methods have proposed spiking self-attention mechanisms compatible with spiking neural networks, they often face challenges in effective deployment on current neuromorphic platforms. This paper introduces a novel model that combines vision transformers with the Locally Competitive Algorithm (LCA) to facilitate efficient neuromorphic deployment. Our experiments show that ViT-LCA achieves higher accuracy on ImageNet-1K dataset while consuming significantly less energy than other spiking vision transformer counterparts. Furthermore, ViT-LCA's neuromorphic-friendly design allows for more direct mapping onto current neuromorphic architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00140
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ViT-LCA: A Neuromorphic Approach for Vision Transformers
Takaghaj, Sanaz Mahmoodi
Neural and Evolutionary Computing
Emerging Technologies
The recent success of Vision Transformers has generated significant interest in attention mechanisms and transformer architectures. Although existing methods have proposed spiking self-attention mechanisms compatible with spiking neural networks, they often face challenges in effective deployment on current neuromorphic platforms. This paper introduces a novel model that combines vision transformers with the Locally Competitive Algorithm (LCA) to facilitate efficient neuromorphic deployment. Our experiments show that ViT-LCA achieves higher accuracy on ImageNet-1K dataset while consuming significantly less energy than other spiking vision transformer counterparts. Furthermore, ViT-LCA's neuromorphic-friendly design allows for more direct mapping onto current neuromorphic architectures.
title ViT-LCA: A Neuromorphic Approach for Vision Transformers
topic Neural and Evolutionary Computing
Emerging Technologies
url https://arxiv.org/abs/2411.00140