In explainable artificial intelligence, discriminative feature localization is critical to reveal a blackbox model's decision-making process from raw data to prediction. In this article, we use two real datasets, the MNIST handwritten digits and MIT-BIH Electrocardiogram (ECG) signals, to motivate key characteristics of discriminative features, namely adaptiveness, predictive importance and effectiveness. Then, we develop a localization framework based on adversarial attacks to effectively localize discriminative features. In contrast to existing heuristic methods, we also provide a statistically guaranteed interpretability of the localized features by measuring a generalized partial $R^2$. We apply the proposed method to the MNIST dataset and the MIT-BIH dataset with a convolutional auto-encoder. In the first, the compact image regions localized by the proposed method are visually appealing. Similarly, in the second, the identified ECG features are biologically plausible and consistent with cardiac electrophysiological principles while locating subtle anomalies in a QRS complex that may not be discernible by the naked eye. Overall, the proposed method compares favorably with state-of-the-art competitors. Accompanying this paper is a Python library dnn-locate (https://dnn-locate.readthedocs.io/en/latest/) that implements the proposed approach.

本文利用两个真实数据集，通过两个关键特征：自适应性、预测重要性和有效性，提出了基于对抗攻击的特征定位框架，通过测量广义偏相关系数来提供定位到的特征的统计确信度，并将所提出的方法应用于 MNIST 和 MIT-BIH 数据集的卷积自编码器，与现有的启发式方法相比，该方法表现优异。同时，配套的 Python 库 dnn-locate 实现了所提出的方法。

具有统计保证的数据自适应的判别特征定位