Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) method
作者：
Highlights：
• A novel XAI explanation method denoted SIDU that can effectively localize entire object regions responsible for prediction in a full extend is introduced.
• The method generates masks and computes similarity differences and uniqueness of the predictions score of mask and original image for explaining the model decision.
• The method is evaluated on three different types evaluations namely Human-Grounded evaluation, Functionally Grounded and Application-Grounded evaluations to thoroughly assess SIDU.
• For the human grounded evaluation, a framework for evaluating explainable AI (XAI) methods using an eye-tracker is introduced.
• The robustness of the SIDU’s explanations analyzed in the presence of adversarial attacks.
摘要
•A novel XAI explanation method denoted SIDU that can effectively localize entire object regions responsible for prediction in a full extend is introduced.•The method generates masks and computes similarity differences and uniqueness of the predictions score of mask and original image for explaining the model decision.•The method is evaluated on three different types evaluations namely Human-Grounded evaluation, Functionally Grounded and Application-Grounded evaluations to thoroughly assess SIDU.•For the human grounded evaluation, a framework for evaluating explainable AI (XAI) methods using an eye-tracker is introduced.•The robustness of the SIDU’s explanations analyzed in the presence of adversarial attacks.
论文关键词：Explainable AI (XAI),CNN,Adversarial attack,Eye-tracker
论文评审过程：Received 24 January 2021, Revised 4 January 2022, Accepted 21 February 2022, Available online 23 February 2022, Version of Record 26 February 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108604
