Convolutional neural networks (CNNs) have been successfully used in a range
of tasks. However, CNNs are often viewed as "black-box" and lack of
interpretability. One main reason is due to the filter-class entanglement -- an
intricate many-to-many correspondence between filters and classes. Most
existing works attempt post-hoc interpretation on a pre-trained model, while
neglecting to reduce the entanglement underlying the model. In contrast, we
focus on alleviating filter-class entanglement during training. Inspired by
cellular differentiation, we propose a novel strategy to train interpretable
CNNs by encouraging class-specific filters, among which each filter responds to
only one (or few) class. Concretely, we design a learnable sparse
Class-Specific Gate (CSG) structure to assign each filter with one (or few)
class in a flexible way. The gate allows a filter's activation to pass only
when the input samples come from the specific class. Extensive experiments
demonstrate the fabulous performance of our method in generating a sparse and
highly class-related representation of the input, which leads to stronger
interpretability. Moreover, comparing with the standard training strategy, our
model displays benefits in applications like object localization and
adversarial sample detection. Code link: this https URL

本文主要介绍了一个用于训练卷积神经网络的新策略，通过向网络中添加可学习的稀疏 Class-Specific Gate 结构，以鼓励针对每个类别的滤波器，从而减轻 “黑盒” 问题和滤波器 - 类别缠结问题；通过在对象定位和对抗样本检测等应用中的实验证明，该方法比标准训练策略更加优异。