Bridging Human Concepts and Computer Vision for Explainable Face Verification

arXiv:2403.08789v1 Announce Type: cross
Abstract: With Artificial Intelligence (AI) influencing the decision-making process of sensitive applications such as Face Verification, it is fundamental to ensure the transparency, fairness, and accountability of decisions. Although Explainable Artificial Intelligence (XAI) techniques exist to clarify AI decisions, it is equally important to provide interpretability of these decisions to humans. In this paper, we present an approach to combine computer and human vision to increase the explanation's interpretability of a face verification algorithm. In particular, …

abstract accountability ai decisions applications artificial artificial intelligence arxiv computer computer vision concepts cs.ai cs.cv cs.hc cs.lg decision decisions explainable artificial intelligence face fairness human intelligence interpretability making process transparency type verification vision xai