Search Results for author:
Found 9 papers, 0 papers with code
On the stability, correctness and plausibility of visual explanation methods based on feature importance
In the field of Explainable AI, multiples evaluation metrics have been proposed in order to assess the quality of explanation methods w. r. t.
Sanity checks for patch visualisation in prototype-based image classification
In this work, we perform an analysis of the visualisation methods implemented in ProtoPNet and ProtoTree, two self-explaining visual classifiers based on prototypes.
Contextualised Out-of-Distribution Detection using Pattern Identication
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-Distribution (OoD) detection method for visual classifiers.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Interpretable Out-Of-Distribution Detection Using Pattern Identification
Out-of-distribution (OoD) detection for data-based programs is a goal of paramount importance.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Sanity checks and improvements for patch visualisation in prototype-based image classification
In this work, we perform an in-depth analysis of the visualisation methods implemented in two popular self-explaining models for visual classification based on prototypes - ProtoPNet and ProtoTree.
PARTICUL: Part Identification with Confidence measure using Unsupervised Learning
We apply our method on two public fine-grained datasets (Caltech-UCSD Bird 200 and Stanford Cars) and show that our detectors can consistently highlight parts of the object while providing a good measure of the confidence in their prediction.
CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustness
We present CAISAR, an open-source platform under active development for the characterization of AI systems' robustness and safety.
DISCO Verification: Division of Input Space into COnvex polytopes for neural network verification
The impressive results of modern neural networks partly come from their non linear behaviour.
CAMUS: A Framework to Build Formal Specifications for Deep Perception Systems Using Simulators
We propose to take advantage of the simulators often used either to train machine learning models or to check them with statistical tests, a growing trend in industry.
