4 papers
Improving segmentation of retinal arteries and veins using cardiac signal in doppler holograms
Marius Dubosc, Yann Fischer, Zacharie Auray +4
Doppler holography is an emerging retinal imaging technique that captures the dynamic behavior of blood flow with high temporal resolution, enabling quantitative assessment of reti…
Explaning with trees: interpreting CNNs using hierarchies
Caroline Mazini Rodrigues, Nicolas Boutry, Laurent Najman
Challenges persist in providing interpretable explanations for neural network reasoning in explainable AI (xAI). Existing methods like Integrated Gradients produce noisy maps, and…
Strong relations between discrete surfaces, poset-based connected manifolds, and normal pseudomanifolds
Nicolas Boutry
In this paper, we study some relationships existing between some particular mathematical structures: discrete surfaces coming from discrete topology and mathematical morphology, po…
Found in Translation: semantic approaches for enhancing AI interpretability in face verification
Miriam Doh, Caroline Mazini Rodrigues, N. Boutry +3
The increasing complexity of machine learning models in computer vision, particularly in face verification, requires the development of explainable artificial intelligence (XAI) to…