arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.11924cs.CVcs.LG
收藏

为正确的理由而正确:使图像分类稳健

Right for the Right Reason: Making Image Classification Robust

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

Anna Nguyen, Adrian Oberföll, Michael Färber

摘要:

卷积神经网络(CNN)在图像数据分类中的有效性已得到充分证明。为了向人类解释分类,近年来已经开发了用于可视化分类证据的方法。这些解释表明,有时图像被正确分类,但由于错误的原因,即,基于偶然的证据当然,期望图像由于正确的原因而被正确地分类,即,基于实际证据。为此,我们提出了一个新的解释质量度量来衡量对象对齐的解释在图像分类,我们称之为ObAlExmetric。使用目标检测方法,解释方法和ObAlEx,我们量化了CNN对实际证据的关注。此外,我们还证明了CNN的额外训练可以提高CNN的焦点,而不会降低其准确性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑