5 papers
Energy-Regularized Spatial Masking: A Novel Approach to Enhancing Robustness and Interpretability in Vision Models
Tom Devynck, Bilal Faye, Djamel Bouchaffra +3
Deep convolutional neural networks achieve remarkable performance by exhaustively processing dense spatial feature maps, yet this brute-force strategy introduces significant comput…
Optimizing Ethical Risk Reduction for Medical Intelligent Systems with Constraint Programming
Clotilde Brayé, Aurélien Bricout, Arnaud Gotlieb +2
Medical Intelligent Systems (MIS) are increasingly integrated into healthcare workflows, offering significant benefits but also raising critical safety and ethical concerns. Accord…
Rashomon in the Streets: Explanation Ambiguity in Scene Understanding
Helge Spieker, Jørn Eirik Betten, Arnaud Gotlieb +2
Explainable AI (XAI) is essential for validating and trusting models in safety-critical applications like autonomous driving. However, the reliability of XAI is challenged by the R…
Metamorphic Testing of Multimodal Human Trajectory Prediction
Helge Spieker, Nadjib Lazaar, Arnaud Gotlieb +1
Context: Predicting human trajectories is crucial for the safety and reliability of autonomous systems, such as automated vehicles and mobile robots. However, rigorously testing th…
Explainable Scene Understanding with Qualitative Representations and Graph Neural Networks
Nassim Belmecheri, Arnaud Gotlieb, Nadjib Lazaar +1
This paper investigates the integration of graph neural networks (GNNs) with Qualitative Explainable Graphs (QXGs) for scene understanding in automated driving. Scene understanding…