arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.08789cs.CVcs.AIcs.HCcs.LG

弥合人类概念与计算机视觉以实现可解释的人脸验证

Bridging Human Concepts and Computer Vision for Explainable Face Verification

  • Université de Mons (UMONS)(蒙斯大学)
  • Université Libre de Bruxelles (ULB)(布鲁塞尔自由大学)
  • EPITA(埃皮塔学院)
  • Université Gustave-Eiffel(古斯塔夫·埃菲尔大学)

机构由 AI 辅助整理,请以论文原文为准。

Miriam Doh, Caroline Mazini Rodrigues, Nicolas Boutry, Laurent Najman, Matei Mancas, Hugues Bersini

更新

AI总结:

本文提出结合计算机与人类视觉的方法,利用Mediapipe分割人脸语义区域并改编两种模型无关算法,提升人脸验证决策的可解释性。

AI中文摘要:

随着人工智能(AI)影响人脸验证等敏感应用的决策过程,确保决策的透明度、公平性和问责制变得至关重要。尽管存在可解释人工智能(XAI)技术来阐明AI决策,但同样重要的是向人类提供这些决策的可解释性。在本文中,我们提出了一种结合计算机视觉和人类视觉的方法,以提高人脸验证算法解释的可解释性。具体而言,我们受人类感知过程的启发,以理解机器在人脸比较任务中如何感知人脸的人类语义区域。我们使用Mediapipe,它提供了一种分割技术,能够识别不同的人类语义面部区域,从而实现对机器感知的分析。此外,我们改编了两种模型无关的算法,以提供关于决策过程的人类可解释的洞察。

英文摘要:

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.

↑