Interpretable Convolutional Neural Networks

Abstract

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.

In this version, we release the website of the code. Compared to the previous version, we have corrected all values of location instability in Table 3--6 by dividing the values by sqrt(2), i.e., a=a/sqrt(2). Such revisions do NOT decrease the significance of the superior performance of our method, because we make the same correction to location-instability values of all baselines

References in corpus (9)

• Deep Residual Learning for Image Recognition
• Learning Deep Features for Discriminative Localization
• Harnessing Deep Neural Networks with Logic Rules
• Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
• Understanding Deep Image Representations by Inverting Them
• Towards Transparent AI Systems: Interpreting Visual Question Answering Models
• Part Detector Discovery in Deep Convolutional Neural Networks
• Understanding deep features with computer-generated imagery
• Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks

Cited by in corpus (13)

• AutoEmbedder: A semi-supervised DNN embedding system for clustering
• Visual Interpretability for Deep Learning: a Survey
• Teaching Categories to Human Learners with Visual Explanations
• Class Activation Map Generation by Representative Class Selection and Multi-Layer Feature Fusion
• Interpretable Convolutional Neural Networks via Feedforward Design
• Towards Interpretable Face Recognition
• A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks
• What's in the box? Explaining the black-box model through an evaluation of its interpretable features
• Transparent Classification with Multilayer Logical Perceptrons and Random Binarization
• Out of the Black Box: Properties of deep neural networks and their applications
• Semi-supervised learning via Feedforward-Designed Convolutional Neural Networks
• Ensembles of feedforward-designed convolutional neural networks
• Crowding in humans is unlike that in convolutional neural networks