Evaluating Saliency Map Explanations for Convolutional Neural Networks: A User Study

Abstract

Convolutional neural networks (CNNs) offer great machine learning performance over a range of applications, but their operation is hard to interpret, even for experts. Various explanation algorithms have been proposed to address this issue, yet limited research effort has been reported concerning their user evaluation. In this paper, we report on an online between-group user study designed to evaluate the performance of "saliency maps" - a popular explanation algorithm for image classification applications of CNNs. Our results indicate that saliency maps produced by the LRP algorithm helped participants to learn about some specific image features the system is sensitive to. However, the maps seem to provide very limited help for participants to anticipate the network's output for new images. Drawing on our findings, we highlight implications for design and further research on explainable AI. In particular, we argue the HCI and AI communities should look beyond instance-level explanations.

10 pages, 6 figures, accepted long paper for ACM IUI 2020

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Towards A Rigorous Science of Interpretable Machine Learning

Cited by in corpus (6)

• Expanding Explainability: Towards Social Transparency in AI systems
• Explainable Deep Reinforcement Learning: State of the Art and Challenges
• Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAI
• Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision Making
• Roadmap of Designing Cognitive Metrics for Explainable Artificial Intelligence (XAI)
• Representaciones del aprendizaje reutilizando los gradientes de la retropropagacion