Alfred Laugros
Research Subjects
Alfred Laugros has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Alice Caplier
Univ. Grenoble Alpes CNRS Grenoble INP GIPSA-lab 38000 Grenoble France
2 shared publications - Matthieu Ospici
Atos
2 shared publications
Latest Publications
- Open Access
Using Synthetic Corruptions to Measure Robustness to Natural Distribution Shifts
Synthetic corruptions gathered into a benchmark are frequently used to measure neural network robustness to distribution shifts. However, robustness to synthetic corruption benchmarks is not always predictive of robustness to distribution shifts encountered in real-world applications. In this paper, we propose a methodology to build synthetic corruption benchmarks that make robustness estimations more correlated with robustness to real-world distribution shifts. Using the overlapping criterion, we split synthetic corruptions into categories that help to better understand neural network robustness. Based on these categories, we identify three relevant parameters to take into account when constructing a corruption benchmark that are the (1) number of represented categories, (2) their relative balance in terms of size and, (3) the size of the considered benchmark. In doing so, we build new synthetic corruption selections that are more predictive of robustness to natural corruptions than existing synthetic corruption benchmarks.
Open AccessUsing Synthetic Corruptions to Measure Robustness to Natural Distribution Shifts
Synthetic corruptions gathered into a benchmark are frequently used to measure neural network robustness to distribution shifts. However, robustness to synthetic corruption benchmarks is not always predictive of robustness to distribution shifts encountered in real-world applications. In this paper, we propose a methodology to build synthetic corruption benchmarks that make robustness estimations more correlated with robustness to real-world distribution shifts. Using the overlapping criterion, we split synthetic corruptions into categories that help to better understand neural network robustness. Based on these categories, we identify three relevant parameters to take into account when constructing a corruption benchmark that are the (1) number of represented categories, (2) their relative balance in terms of size and, (3) the size of the considered benchmark. In doing so, we build new synthetic corruption selections that are more predictive of robustness to natural corruptions than existing synthetic corruption benchmarks.
- 1 January 2020
- Published by Springer Nature
- p. 178-195
Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Training
- 1 January 2020
- Published by Springer Nature
- p. 178-195
Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Training