CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision Models

arXiv:2404.14830v1 Announce Type: new
Abstract: Mounting evidence in explainability for artificial intelligence (XAI) research suggests that good explanations should be tailored to individual tasks and should relate to concepts relevant to the task. However, building task specific explanations is time consuming and requires domain expertise which can be difficult to integrate into generic XAI methods. A promising approach towards designing useful task specific explanations with domain experts is based on compositionality of semantic concepts. Here, we present a novel approach …

arxiv concept cs.ai cs.cv neighbors type vision vision models