This paper proposes a method to modify traditional convolutional neural
networks (CNNs) into interpretable CNNs, in order to clarify knowledge
representations in high conv-layers of CNNs. In an interpretable CNN, each
filter in a high conv-layer represents a certain object part. We do not need
any annotations of object parts or textures to supervise the learning process.
Instead, the interpretable CNN automatically assigns each filter in a high
conv-layer with an object part during the learning process. Our method can be
applied to different types of CNNs with different structures. The clear
knowledge representation in an interpretable CNN can help people understand the
logics inside a CNN, i.e., based on which patterns the CNN makes the decision.
Experiments showed that filters in an interpretable CNN were more semantically
meaningful than those in traditional CNNs.

本文提出了一种方法，将传统的 CNN 转换为可解释的 CNN，以澄清 CNN 高卷积层中的知识表示。在可解释的 CNN 中，高卷积层中的每个滤波器表示某个物体部分，无需任何部件或纹理的注释就可以在学习过程中自动分配。实验表明，可解释的 CNN 中的滤波器比传统 CNN 中的滤波器更具有语义意义。