Crowdsourcing Evaluation of Saliency-Based XAI Methods

• Published in: Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track Vol. 12979; pp. 431 - 446
• Main Authors: Lu, Xiaotian, Tolmachev, Arseny, Yamamoto, Tatsuya, Takeuchi, Koh, Okajima, Seiji, Takebayashi, Tomoyoshi, Maruhashi, Koji, Kashima, Hisashi
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2021; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Crowdsourcing; Evaluation; Explainable AI; Interpretability

Understanding the reasons behind the predictions made by deep neural networks is critical for gaining human trust in many important applications, which is reflected in the increasing demand for explainability in AI (XAI) in recent years. Saliency-based feature attribution methods, which highlight im...