论文标题
正确的原因是：使图像分类鲁棒
Right for the Right Reason: Making Image Classification Robust
论文作者
论文摘要
已经彻底证明了卷积神经网络（CNN）对图像数据进行分类的有效性。为了解释对人类的分类，近年来已经开发了可视化分类证据的方法。这些解释表明，有时将图像正确地分类，但出于错误的原因，即基于偶然证据。当然，希望出于正确的原因（即基于实际证据）正确对图像进行正确的分类。为此，我们提出了一个新的解释质量度量标准，以测量对象在图像分类中对齐的解释，我们称为theobalexmetric。使用对象检测方法，解释方法和Obalex，我们量化了CNN的重点放在实际证据上。此外，我们表明，对CNN的额外培训可以改善CNN的重点而不降低其准确性。
The effectiveness of Convolutional Neural Networks (CNNs)in classifying image data has been thoroughly demonstrated. In order to explain the classification to humans, methods for visualizing classification evidence have been developed in recent years. These explanations reveal that sometimes images are classified correctly, but for the wrong reasons,i.e., based on incidental evidence. Of course, it is desirable that images are classified correctly for the right reasons, i.e., based on the actual evidence. To this end, we propose a new explanation quality metric to measure object aligned explanation in image classification which we refer to as theObAlExmetric. Using object detection approaches, explanation approaches, and ObAlEx, we quantify the focus of CNNs on the actual evidence. Moreover, we show that additional training of the CNNs can improve the focus of CNNs without decreasing their accuracy.
