6 papers
Robust Validation to Geometric Perturbations for Autonomous Pose Estimation
Gregoire Theau, Melanie Ducoffe
Deploying autonomous systems in safety-critical domains demands guaranteed robustness against physically plausible geometric perturbations rather than abstract pixel-wise noise. In…
Certified geometric robustness -- Super-DeepG
Noémie Cohen, Mélanie Ducoffe, Christophe Gabreau +2
Safety-critical applications are required to perform as expected in normal operations. Image processing functions are often required to be insensitive to small geometric perturbati…
LARD 2.0: Enhanced Datasets and Benchmarking for Autonomous Landing Systems
Yassine Bougacha, Geoffrey Delhomme, Mélanie Ducoffe +8
This paper addresses key challenges in the development of autonomous landing systems, focusing on dataset limitations for supervised training of Machine Learning (ML) models for ob…
FAME: Formal Abstract Minimal Explanation for Neural Networks
Ryma Boumazouza, Raya Elsaleh, Melanie Ducoffe +2
We propose FAME (Formal Abstract Minimal Explanations), a new class of abductive explanations grounded in abstract interpretation. FAME is the first method to scale to large neural…
VerifIoU -- Robustness of Object Detection to Perturbations
Noémie Cohen, Mélanie Ducoffe, Ryma Boumazouza +4
We introduce a novel Interval Bound Propagation (IBP) approach for the formal verification of object detection models, specifically targeting the Intersection over Union (IoU) metr…
Robust Vision-Based Runway Detection through Conformal Prediction and Conformal mAP
Alya Zouzou, Léo andéol, Mélanie Ducoffe +1
We explore the use of conformal prediction to provide statistical uncertainty guarantees for runway detection in vision-based landing systems (VLS). Using fine-tuned YOLOv5 and YOL…