论文标题
用计数器视觉属性和示例解释
Explaining with Counter Visual Attributes and Examples
论文作者
论文摘要
在本文中，我们旨在通过使用多模式信息来解释神经网络的决定。这是违反直觉属性和反视觉示例，当引入扰动样品时出现。与以前有关使用显着图，文本或视觉贴片来解释决策的工作不同，我们建议使用属性和反归因于属性，以及作为视觉解释的一部分示例和反例。当人类解释视觉决定时，他们倾向于通过提供属性和示例来做到这一点。因此，受到本文人类解释方式的启发，我们提供了基于属性的示例解释。此外，人类还倾向于通过添加反归因和反示例来解释未看到的内容来解释其视觉决策。我们在示例中介绍了定向的扰动，以观察哪些属性值在将示例分类为计数类中时会发生变化。这提供了直观的反归因和反例。我们对粗粒和细粒数据集进行的实验表明，属性提供了歧视和人为理解的直觉和违反直觉的解释。
In this paper, we aim to explain the decisions of neural networks by utilizing multimodal information. That is counter-intuitive attributes and counter visual examples which appear when perturbed samples are introduced. Different from previous work on interpreting decisions using saliency maps, text, or visual patches we propose to use attributes and counter-attributes, and examples and counter-examples as part of the visual explanations. When humans explain visual decisions they tend to do so by providing attributes and examples. Hence, inspired by the way of human explanations in this paper we provide attribute-based and example-based explanations. Moreover, humans also tend to explain their visual decisions by adding counter-attributes and counter-examples to explain what is not seen. We introduce directed perturbations in the examples to observe which attribute values change when classifying the examples into the counter classes. This delivers intuitive counter-attributes and counter-examples. Our experiments with both coarse and fine-grained datasets show that attributes provide discriminating and human-understandable intuitive and counter-intuitive explanations.
