Evaluating the Explainability of Attributes and Prototypes for a Medical Classification Model

arXiv:2404.09917v1 Announce Type: new
Abstract: Due to the sensitive nature of medicine, it is particularly important and highly demanded that AI methods are explainable. This need has been recognised and there is great research interest in xAI solutions with medical applications. However, there is a lack of user-centred evaluation regarding the actual impact of the explanations. We evaluate attribute- and prototype-based explanations with the Proto-Caps model. This xAI model reasons the target classification with human-defined visual features of the target …

abstract applications arxiv classification classification model cs.cv explainability however medical medicine nature research solutions type xai