4 papers
There is More to Attention: Statistical Filtering Enhances Explanations in Vision Transformers
Meghna P Ayyar, Jenny Benois-Pineau, Akka Zemmari
Explainable AI (XAI) has become increasingly important with the rise of large transformer models, yet many explanation methods designed for CNNs transfer poorly to Vision Transform…
FusWay: Multimodal hybrid fusion approach. Application to Railway Defect Detection
Alexey Zhukov, Jenny Benois-Pineau, Amira Youssef +3
Multimodal fusion is a multimedia technique that has become popular in the wide range of tasks where image information is accompanied by a signal/audio. The latter may not convey h…
Mean Opinion Score as a New Metric for User-Evaluation of XAI Methods
Hyeon Yu, Jenny Benois-Pineau, Romain Bourqui +2
This paper investigates the use of Mean Opinion Score (MOS), a common image quality metric, as a user-centric evaluation metric for XAI post-hoc explainers. To measure the MOS, a u…
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…