SCOUT: Self-Aware Discriminant Counterfactual Explanations
SCOUT: Self-Aware Discriminant Counterfactual Explanations
复制标题
DOI：
10.1109/cvpr42600.2020.00900
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Pei Wang;N. Vasconcelos
中科院分区：
文献类型：
--
作者：
Pei Wang;N. Vasconcelos
考虑了反事实的视觉解释问题。介绍了一类新的判别解释。这些生成的热图将高分归给分类器预测信息的图像区域，而不是计数器类。他们将基于单一热图的定语解释与反事实解释联系起来，后者同时解释了预测类和反类。后者被证明是可计算的两个区别解释的组合，与反向类对。有人认为，自我意识，即产生分类置信度分数的能力，对于判别解释的计算很重要，判别解释寻求识别容易区分预测类和反类的区域。这表明可以通过三种归因图的组合来计算判别解释。得到的反事实解释不需要优化，因此比以前的方法快得多。为了解决其评估的困难，还提出了一个代理任务和一套定量指标。根据该协议进行的实验表明，对于流行的网络，所提出的反事实解释在速度上要快得多，而且优于目前的技术水平。在一个人类学习机器教学实验中，它们也被证明可以将学生的平均准确率从偶然水平提高到95%。
The problem of counterfactual visual explanations is considered. A new family of discriminant explanations is introduced. These produce heatmaps that attribute high scores to image regions informative of a classifier prediction but not of a counter class. They connect attributive explanations, which are based on a single heat map, to counterfactual explanations, which account for both predicted class and counter class. The latter are shown to be computable by combination of two discriminant explanations, with reversed class pairs. It is argued that self-awareness, namely the ability to produce classification confidence scores, is important for the computation of discriminant explanations, which seek to identify regions where it is easy to discriminate between prediction and counter class. This suggests the computation of discriminant explanations by the combination of three attribution maps. The resulting counterfactual explanations are optimization free and thus much faster than previous methods. To address the difficulty of their evaluation, a proxy task and set of quantitative metrics are also proposed. Experiments under this protocol show that the proposed counterfactual explanations outperform the state of the art while achieving speeds much faster, for popular networks. In a human-learning machine teaching experiment, they are also shown to improve mean student accuracy from chance level to 95%.