Explaining Convolutional Neural Networks by Tagging Filters
This addresses the interpretability issue in CNNs for non-experts, though it is incremental as it builds on existing visualization methods.
The paper tackles the problem of explaining convolutional neural network (CNN) classifications to non-experts by proposing FilTag, which tags filters with classes based on activation patterns, resulting in intuitive explanations for individual image classifications and utility in analyzing errors and machine processing.
Convolutional neural networks (CNNs) have achieved astonishing performance on various image classification tasks, but it is difficult for humans to understand how a classification comes about. Recent literature proposes methods to explain the classification process to humans. These focus mostly on visualizing feature maps and filter weights, which are not very intuitive for non-experts in analyzing a CNN classification. In this paper, we propose FilTag, an approach to effectively explain CNNs even to non-experts. The idea is that when images of a class frequently activate a convolutional filter, then that filter is tagged with that class. These tags provide an explanation to a reference of a class-specific feature detected by the filter. Based on the tagging, individual image classifications can then be intuitively explained in terms of the tags of the filters that the input image activates. Finally, we show that the tags are helpful in analyzing classification errors caused by noisy input images and that the tags can be further processed by machines.