research
∙
09/14/2023
BEA: Revisiting anchor-based object detection DNN using Budding Ensemble Architecture
This paper introduces the Budding Ensemble Architecture (BEA), a novel r...
share
research
∙
07/21/2023
Envisioning a Safety Island to Enable HPC Devices in Safety-Critical Domains
HPC (High Performance Computing) devices increasingly become the only al...
research
∙
03/15/2023
Exploring Resiliency to Natural Image Corruptions in Deep Learning using Design Diversity
In this paper, we investigate the relationship between diversity metrics...
research
∙
03/03/2023
Evaluation of Confidence-based Ensembling in Deep Learning Image Classification
Ensembling is a successful technique to improve the performance of machi...
research
∙
12/09/2022
Reliable Multimodal Trajectory Prediction via Error Aligned Uncertainty Optimization
Reliable uncertainty quantification in deep neural networks is very cruc...
research
∙
09/07/2022
Hardware faults that matter: Understanding and Estimating the safety impact of hardware faults on object detection DNNs
Object detection neural network models need to perform reliably in highl...
research
∙
11/24/2021
Fault-Tolerant Perception for Automated Driving A Lightweight Monitoring Approach
While the most visible part of the safety verification process of automa...
research
∙
08/16/2021