Bandit Interpretability of Deep Models via Confidence Selection.

Xiaoyue Duan,Hong Li,Panpan Wang,Tiancheng Wang,Boyu Liu,Baochang Zhang

Neurocomputing（2023）

引用 0|浏览13

暂无评分

摘要

•We are the first to formulate the interpretation of deep models as a bandit problem.•Our statistical perturbations retain regional interaction without any prior involved.•The Upper Confidence Bound guarantees a fair selection of critical image features.•Our method provides more precise explanations with a smaller area.

查看译文

关键词

Interpretability,Deep neural networks,Multi-armed bandit problem,The upper confidence bounds,Statistical perturbation

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要