A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks
This work provides a structured framework and tool for researchers to better interpret CNN features, though it is incremental as it organizes existing methods rather than introducing new ones.
The authors tackled the challenge of understanding learned features in convolutional neural networks by proposing a taxonomy to classify visualization methods and introducing an open-source library for visualizing CNNs, which aids in analyzing intermediate layers and network failures.
Over the last decade, Convolutional Neural Networks (CNN) saw a tremendous surge in performance. However, understanding what a network has learned still proves to be a challenging task. To remedy this unsatisfactory situation, a number of groups have recently proposed different methods to visualize the learned models. In this work we suggest a general taxonomy to classify and compare these methods, subdividing the literature into three main categories and providing researchers with a terminology to base their works on. Furthermore, we introduce the FeatureVis library for MatConvNet: an extendable, easy to use open source library for visualizing CNNs. It contains implementations from each of the three main classes of visualization methods and serves as a useful tool for an enhanced understanding of the features learned by intermediate layers, as well as for the analysis of why a network might fail for certain examples.