Explaining predictions of deep neural networks (DNNs) is an important and
nontrivial task. In this paper, we propose a practical approach to interpret
decisions made by a DNN object detector that has fidelity comparable to
state-of-the-art methods and sufficient computational efficiency to process
large datasets. Our method relies on recent theory and approximates Shapley
feature importance values. We qualitatively and quantitatively show that the
proposed explanation method can be used to find image features which cause
failures in DNN object detection. The developed software tool combined into the
"Explain to Fix" (E2X) framework has a factor of 10 higher computational
efficiency than prior methods and can be used for cluster processing using
graphics processing units (GPUs). Lastly, we propose a potential extension of
the E2X framework where the discovered missing features can be added into
training dataset to overcome failures after model retraining.

本文提出了一种实用的方法，通过使用最近的理论并近似 Shapley 特征重要性值解释 DNN 目标检测器所做的决策，该方法具有与最先进方法可比的保真度和足够的计算效率，可以处理大型数据集。我们在质量和数量方面展示了所提出的解释方法可用于查找导致 DNN 目标检测失败的图像特征。开发的软件工具结合到 “解释到修复”（E2X）框架中，其计算效率比先前的方法高出一个数量级，可以使用图形处理单元（GPUs）进行集群处理。最后，我们提出了 E2X 框架的一个潜在扩展，即可以将发现丢失的特征添加到训练数据集中，以克服模型重新训练后的失败。