Details

Autor(en) / Beteiligte

• Kim, Sunnie S. Y.
• Meister, Nicole
• Ramaswamy, Vikram V.
• Fong, Ruth
• Russakovsky, Olga
• Avidan, Shai
• Cissé, Moustapha
• Brostow, Gabriel
• Hassner, Tal
• Farinella, Giovanni Maria

Titel

HIVE: Evaluating the Human Interpretability of Visual Explanations

Ist Teil von

• Computer Vision - ECCV 2022, 2022, Vol.13672, p.280-298

Ort / Verlag

Switzerland: Springer

Erscheinungsjahr

2022

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• As AI technology is increasingly applied to high-impact, high-risk domains, there have been a number of new methods aimed at making AI models more human interpretable. Despite the recent growth of interpretability work, there is a lack of systematic evaluation of proposed techniques. In this work, we introduce HIVE (Human Interpretability of Visual Explanations), a novel human evaluation framework that assesses the utility of explanations to human users in AI-assisted decision making scenarios, and enables falsifiable hypothesis testing, cross-method comparison, and human-centered evaluation of visual interpretability methods. To the best of our knowledge, this is the first work of its kind. Using HIVE, we conduct IRB-approved human studies with nearly 1000 participants and evaluate four methods that represent the diversity of computer vision interpretability works: GradCAM, BagNet, ProtoPNet, and ProtoTree. Our results suggest that explanations engender human trust, even for incorrect predictions, yet are not distinct enough for users to distinguish between correct and incorrect predictions. We open-source HIVE to enable future studies and encourage more human-centered approaches to interpretability research. HIVE can be found at https://princetonvisualai.github.io/HIVE.