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

TL;DR

This paper assesses the vulnerability of embedded deep neural networks for semantic segmentation to single event upsets, analyzing layer sensitivity and proposing lightweight error mitigation techniques suitable for resource-constrained edge devices.

Contribution

It provides a detailed layer-by-layer and bit-by-bit analysis of SEU impacts on CNNs for segmentation and introduces practical, low-cost error mitigation strategies for embedded AI systems.

Findings

SEUs significantly affect CNN segmentation accuracy.

Model pruning and quantization influence robustness.

Proposed lightweight mitigation techniques improve reliability.

Abstract

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 .