Bridging Human Concepts and Computer Vision for Explainable Face Verification
This addresses the need for transparency and fairness in sensitive AI applications like face verification, though it appears incremental by building on existing XAI techniques.
The paper tackles the problem of making face verification algorithms more interpretable to humans by combining computer and human vision, using Mediapipe for facial region segmentation and adapting model-agnostic algorithms to provide insights.
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, we are inspired by the human perceptual process to understand how machines perceive face's human-semantic areas during face comparison tasks. We use Mediapipe, which provides a segmentation technique that identifies distinct human-semantic facial regions, enabling the machine's perception analysis. Additionally, we adapted two model-agnostic algorithms to provide human-interpretable insights into the decision-making processes.