Search Results for author: Mădălina Eraşcu

Found 2 papers, 2 papers with code

Benchmarking Local Robustness of High-Accuracy Binary Neural Networks for Enhanced Traffic Sign Recognition

1 code implementation25 Sep 2023 Andreea Postovan, Mădălina Eraşcu

The results of the 4th International Verification of Neural Networks Competition (VNN-COMP'23) revealed the fact that 4, out of 7, solvers can handle many of our benchmarks randomly selected (minimum is 6, maximum is 36, out of 45).

Autonomous Driving Benchmarking +1

Architecturing Binarized Neural Networks for Traffic Sign Recognition

4 code implementations27 Mar 2023 Andreea Postovan, Mădălina Eraşcu

Traffic signs support road safety and managing the flow of traffic, hence are an integral part of any vision system for autonomous driving.

Autonomous Driving Traffic Sign Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.