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

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 .

References in corpus (5)

• To prune, or not to prune: exploring the efficacy of pruning for model compression
• Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation
• Improving aircraft performance using machine learning: a review
• HSI-Drive v2.0: More Data for New Challenges in Scene Understanding for Autonomous Driving
• Efficient Post-training Quantization with FP8 Formats

Cited by in corpus (4)

• Designing DNNs for a trade-off between robustness and processing performance in embedded devices
• Reliable Explainability of Deep Learning Spatial-Spectral Classifiers for Improved Semantic Segmentation in Autonomous Driving
• Balancing Robustness and Efficiency in Embedded DNNs Through Activation Function Selection
• Optimization of DNN-based HSI Segmentation FPGA-based SoC for ADS: A Practical Approach