Evaluating Single Event Upsets in Deep Neural Networks for Semantic Segmentation: an embedded system perspective

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gutiérrez-Zaballa, Jon, Basterretxea, Koldo, Echanobe, Javier
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929616707387392
author Gutiérrez-Zaballa, Jon
Basterretxea, Koldo
Echanobe, Javier
author_facet Gutiérrez-Zaballa, Jon
Basterretxea, Koldo
Echanobe, Javier
contents As the deployment of artifical intelligence (AI) algorithms at edge devices becomes increasingly prevalent, enhancing the robustness and reliability of autonomous AI-based perception and decision systems is becoming as relevant as precision and performance, especially in applications areas considered safety-critical such as autonomous driving and aerospace. This paper delves into the robustness assessment in embedded Deep Neural Networks (DNNs), particularly focusing on the impact of parameter perturbations produced by single event upsets (SEUs) on convolutional neural networks (CNN) for image semantic segmentation. By scrutinizing the layer-by-layer and bit-by-bit sensitivity of various encoder-decoder models to soft errors, this study thoroughly investigates the vulnerability of segmentation DNNs to SEUs and evaluates the consequences of techniques like model pruning and parameter quantization on the robustness of compressed models aimed at embedded implementations. The findings offer valuable insights into the mechanisms underlying SEU-induced failures that allow for evaluating the robustness of DNNs once trained in advance. Moreover, based on the collected data, we propose a set of practical lightweight error mitigation techniques with no memory or computational cost suitable for resource-constrained deployments. The code used to perform the fault injection (FI) campaign is available at https://github.com/jonGuti13/TensorFI2 , while the code to implement proposed techniques is available at https://github.com/jonGuti13/parameterProtection .
format Preprint
id arxiv_https___arxiv_org_abs_2412_03630
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluating Single Event Upsets in Deep Neural Networks for Semantic Segmentation: an embedded system perspective
Gutiérrez-Zaballa, Jon
Basterretxea, Koldo
Echanobe, Javier
Computer Vision and Pattern Recognition
Artificial Intelligence
Hardware Architecture
Machine Learning
Image and Video Processing
As the deployment of artifical intelligence (AI) algorithms at edge devices becomes increasingly prevalent, enhancing the robustness and reliability of autonomous AI-based perception and decision systems is becoming as relevant as precision and performance, especially in applications areas considered safety-critical such as autonomous driving and aerospace. This paper delves into the robustness assessment in embedded Deep Neural Networks (DNNs), particularly focusing on the impact of parameter perturbations produced by single event upsets (SEUs) on convolutional neural networks (CNN) for image semantic segmentation. By scrutinizing the layer-by-layer and bit-by-bit sensitivity of various encoder-decoder models to soft errors, this study thoroughly investigates the vulnerability of segmentation DNNs to SEUs and evaluates the consequences of techniques like model pruning and parameter quantization on the robustness of compressed models aimed at embedded implementations. The findings offer valuable insights into the mechanisms underlying SEU-induced failures that allow for evaluating the robustness of DNNs once trained in advance. Moreover, based on the collected data, we propose a set of practical lightweight error mitigation techniques with no memory or computational cost suitable for resource-constrained deployments. The code used to perform the fault injection (FI) campaign is available at https://github.com/jonGuti13/TensorFI2 , while the code to implement proposed techniques is available at https://github.com/jonGuti13/parameterProtection .
title Evaluating Single Event Upsets in Deep Neural Networks for Semantic Segmentation: an embedded system perspective
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Hardware Architecture
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2412.03630