Interpretable Image Recognition with Hierarchical Prototypes
Interpretable Image Recognition with Hierarchical Prototypes
复制标题
具有分层原型的可解释图像识别
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
C. Rudin
中科院分区：
文献类型：
--
作者：
Peter Hase;Chaofan Chen;Oscar Li;C. Rudin
视觉模型是可解释的，当它们根据人可以直接理解的特征对对象进行分类时。最近，基于视觉特征原型的方法已经被开发出来。然而，与人类对对象进行分类的方式不同，这些方法还没有利用任何类标签的分类组织。例如，通过这样的方法，我们可能会明白为什么黑猩猩被归类为黑猩猩，而不是为什么它被认为是灵长类动物，甚至是动物。在这项工作中，我们介绍了一个模型，它使用分层组织的原型来对预定义分类中的每个级别的对象进行分类。因此，我们可能会在分类的每个级别上找到对图像接收的预测的不同解释。分层原型使模型能够执行另一项重要任务：在它们正确相关的分类级别上对来自以前未见的类别的图像进行解释性分类，例如，当训练数据中唯一的武器是步枪时，将手枪归类为武器。使用ImageNet的子集，我们在两个任务上测试了我们的模型与其对应的黑盒模型：1)从熟悉的类中分类数据，以及2)在分类中的适当级别对来自以前未见过的类的数据进行分类。我们发现，在允许解释每一种分类的情况下，我们的模型的表现与其对应的黑盒模型大致相同。
Vision models are interpretable when they classify objects on the basis of features that a person can directly understand. Recently, methods relying on visual feature prototypes have been developed for this purpose. However, in contrast to how humans categorize objects, these approaches have not yet made use of any taxonomical organization of class labels. With such an approach, for instance, we may see why a chimpanzee is classified as a chimpanzee, but not why it was considered to be a primate or even an animal. In this work we introduce a model that uses hierarchically organized prototypes to classify objects at every level in a predefined taxonomy. Hence, we may find distinct explanations for the prediction an image receives at each level of the taxonomy. The hierarchical prototypes enable the model to perform another important task: interpretably classifying images from previously unseen classes at the level of the taxonomy to which they correctly relate, e.g. classifying a hand gun as a weapon, when the only weapons in the training data are rifles. With a subset of ImageNet, we test our model against its counterpart black-box model on two tasks: 1) classification of data from familiar classes, and 2) classification of data from previously unseen classes at the appropriate level in the taxonomy. We find that our model performs approximately as well as its counterpart black-box model while allowing for each classification to be interpreted.