论文标题
ICAPS：通过解开的胶囊网络解释的分类器
iCaps: An Interpretable Classifier via Disentangled Capsule Networks
论文作者
论文摘要
我们提出了一个可解释的胶囊网络，ICAP，用于图像分类。胶囊是嵌套在每一层内的一组神经元，最后一层中的神经元称为类胶囊，该囊是一个向量，其标准表示该类的预测概率。使用类胶囊，现有的胶囊网络已经提供了一定程度的解释性。但是，有两个局限性降低了其可解释性：1）类胶囊还包括分类 - iRrelevant信息，而2）由类胶囊重叠表示的实体。在这项工作中，我们分别使用一种新型的私人监督分解算法和附加的正规化程序来解决这两个局限性。通过在三个数据集上的定量和定性评估，我们证明了所得的分类器ICAPS提供了一个预测以及背后明确的理由，而没有性能降解。
We propose an interpretable Capsule Network, iCaps, for image classification. A capsule is a group of neurons nested inside each layer, and the one in the last layer is called a class capsule, which is a vector whose norm indicates a predicted probability for the class. Using the class capsule, existing Capsule Networks already provide some level of interpretability. However, there are two limitations which degrade its interpretability: 1) the class capsule also includes classification-irrelevant information, and 2) entities represented by the class capsule overlap. In this work, we address these two limitations using a novel class-supervised disentanglement algorithm and an additional regularizer, respectively. Through quantitative and qualitative evaluations on three datasets, we demonstrate that the resulting classifier, iCaps, provides a prediction along with clear rationales behind it with no performance degradation.
