1.5k citations
- Technical University of MunichDE3 papers
- Ericsson (Sweden)SE2 papers
- ETH ZurichCH2 papers
- German Research Centre for Artificial IntelligenceDE2 papers
- Huawei Technologies (Germany)DE2 papers
- Intel (United States)US2 papers
- Jagiellonian UniversityPL2 papers
- Saarland UniversityDE2 papers
- Samsung (United Kingdom)GB2 papers
- Technische Hochschule AugsburgDE2 papers
- APCON (Germany)DE1 paper
- Brookhaven National LaboratoryUS1 paper
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2023★ 8 cited
A Low-cost Strategic Monitoring Approach for Scalable and Interpretable Error Detection in Deep Neural Networks
Florian Geissler, Syed Qutub, Michael Paulitsch +1
We present a highly compact run-time monitoring approach for deep computer vision networks that extracts selected knowledge from only a few (down to merely two) hidden layers, yet…
cs.CV2022★ 8 cited
Hardware faults that matter: Understanding and Estimating the safety impact of hardware faults on object detection DNNs
Syed Qutub, Florian Geissler, Yang Peng +4
Object detection neural network models need to perform reliably in highly dynamic and safety-critical environments like automated driving or robotics. Therefore, it is paramount to…