Litcius/Paper detail

CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models

Arjun Akula, Keze Wang, Changsong Liu, Sari Saba-Sadiya, Hongjing Lu, Siniša Todorović, Joyce Chai, Song‐Chun Zhu

2021iScience59 citationsDOIOpen Access PDF

Abstract

. Extensive experiments verify our hypotheses, demonstrating that our CX-ToM significantly outperforms the state-of-the-art XAI models.

Topics & Concepts

Counterfactual thinkingCognitive scienceTheory of mindPsychologyData scienceComputer scienceEpistemologyPhilosophyNeuroscienceCognitionExplainable Artificial Intelligence (XAI)Adversarial Robustness in Machine LearningEthics and Social Impacts of AI
CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models | Litcius