SCOUT：自我意识判别反事实推理
SCOUT: Self-aware Discriminant Counterfactual Explanations
摘要：
反事实的视觉解释的问题被认为是。引入了一个新的判别式解释族。这些产生的热图将高分归因于提供分类器预测信息但不提供计数器类信息的图像区域。他们将基于单一热图的属性解释与反事实解释联系起来，后者既解释了预测类，又解释了反类。后者被证明是可计算的组合的两个判别式的解释，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，是很重要的判别式解释的计算，寻求识别区域，它是很容易区分预测和计数器类。这表明通过三个属性图的组合来计算判别解释。由此产生的反事实解释是无优化的，因此比以前的方法快得多。为了解决他们的评价困难，代理任务和一套定量指标也提出了。该协议下的实验表明，所提出的反事实解释优于现有技术，同时实现更高的速度，为流行的网络。在人类学习机器教学实验中，它们还将学生的平均准确率从偶然水平提高到95%。
英文摘要：
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 much higher speeds, for popular networks. In a human-learning machine teaching experiment, they are also shown to improve mean student accuracy from chance level to 95\%.
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。
