Matthias Löwe — accepted AI-conference papers

2021

Towards an Intrinsic Definition of Robustness for a Classifier

Théo Giraudon, Vincent Gripon, Matthias Löwe, Franck Vermet

ICASSP 2021accepted

Finding good measures of robustness – i.e. the ability to correctly classify corrupted input signals – of a trained classifier is an important question for sensitive practical applications. In this paper, we point out that averaging the radius of robustness of samples in a validation set is a statis…

Cited by 0 Source ↗Scholar ↗

2018

Improving Accuracy of Nonparametric Transfer Learning Via Vector Segmentation

Vincent Gripon, Ghouthi B. Hacene, Matthias Löwe, Franck Vermet

ICASSP 2018accepted

Transfer learning using deep neural networks as feature extractors has become increasingly popular over the past few years. It allows to obtain state-of-the-art accuracy on datasets too small to train a deep neural network on its own, and it provides cutting edge descriptors that, combined with nonp…

Cited by 0 Source ↗Scholar ↗