Convolutional neural networks (CNNs) achieve state-of-the-art performance in
a wide variety of tasks in computer vision. However, interpreting CNNs still
remains a challenge. This is mainly due to the large number of parameters in
these networks. Here, we investigate the role of compression and particularly
pruning filters in the interpretation of CNNs. We exploit our recently-proposed
greedy structural compression scheme that prunes filters in a trained CNN. In
our compression, the filter importance index is defined as the classification
accuracy reduction (CAR) of the network after pruning that filter. The filters
are then iteratively pruned based on the CAR index. We demonstrate the
interpretability of CAR-compressed CNNs by showing that our algorithm prunes
filters with visually redundant pattern selectivity. Specifically, we show the
importance of shape-selective filters for object recognition, as opposed to
color-selective filters. Out of top 20 CAR-pruned filters in AlexNet, 17 of
them in the first layer and 14 of them in the second layer are color-selective
filters. Finally, we introduce a variant of our CAR importance index that
quantifies the importance of each image class to each CNN filter. We show that
the most and the least important class labels present a meaningful
interpretation of each filter that is consistent with the visualized pattern
selectivity of that filter.

本文探讨了压缩和特别是修剪滤波器在解释卷积神经网络中的作用，并通过 CAR 压缩算法，演示了修剪具有视觉冗余模式选择性的滤波器的可解释性。作者比较了 AlexNet 的前 20 个 CAR 修剪滤波器的颜色选择性和形状选择性，并引入了一个量化每个图像类对 CNN 滤波器的重要性的 CAR 重要性指数，最后发现对每个 CNN 滤波器最重要和不重要的类标签提供了与该滤波器的可视化模式选择性一致的有意义的解释。