activity
20172024
most citedCDCL-inspired Word-level Learning for Bit-vector Constraint Solving

5 citations · 6 across the 7 of their papers we have counts for

collaborators

8 papers

cs.LG2024

On Using Certified Training towards Empirical Robustness

Alessandro De Palma, Serge Durand, Zakaria Chihani +2

Adversarial training is arguably the most popular way to provide empirical robustness against specific adversarial examples. While variants based on multi-step attacks incur signif…

cs.AI2024

CaBRNet, an open-source library for developing and evaluating Case-Based Reasoning Models

Romain Xu-Darme, Aymeric Varasse, Alban Grastien +2

In the field of explainable AI, a vibrant effort is dedicated to the design of self-explainable models, as a more principled alternative to post-hoc methods that attempt to explain…

cs.CV2023

Sanity checks for patch visualisation in prototype-based image classification

Romain Xu-Darme, Georges Quénot, Zakaria Chihani +1

In this work, we perform an analysis of the visualisation methods implemented in ProtoPNet and ProtoTree, two self-explaining visual classifiers based on prototypes. We show that s…

cs.CV2023

On the stability, correctness and plausibility of visual explanation methods based on feature importance

Romain Xu-Darme, Jenny Benois-Pineau, Romain Giot +4

In the field of Explainable AI, multiples evaluation metrics have been proposed in order to assess the quality of explanation methods w.r.t. a set of desired properties. In this wo…

cs.CV2023

Contextualised Out-of-Distribution Detection using Pattern Identication

Romain Xu-Darme, Julien Girard-Satabin, Darryl Hond +2

In this work, we propose CODE, an extension of existing work from the field of explainable AI that identifies class-specific recurring patterns to build a robust Out-of-Distributio…

cs.AI20211 cited

DISCO Verification: Division of Input Space into COnvex polytopes for neural network verification

Julien Girard-Satabin, Aymeric Varasse, Marc Schoenauer +2

The impressive results of modern neural networks partly come from their non linear behaviour. Unfortunately, this property makes it very difficult to apply formal verification tool…