Search Results for author:
Found 5 papers, 1 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.
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.
