Interpretable Convolutional Neural Networks

This paper proposes a method to modify a traditional convolutional neural network (CNN) into an interpretable CNN, in order to clarify knowledge representations in high conv-layers of the CNN. In an interpretable CNN, each filter in a high conv-layer represents a specific object part. Our interpreta...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 8827 - 8836
Main Authors Zhang, Quanshi, Wu, Ying Nian, Zhu, Song-Chun
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Convolutional neural networks
Entropy
Integrated circuits
Semantics
Task analysis
Training
Visualization
Online AccessGet full text

Cover

More Information
Summary:This paper proposes a method to modify a traditional convolutional neural network (CNN) into an interpretable CNN, in order to clarify knowledge representations in high conv-layers of the CNN. In an interpretable CNN, each filter in a high conv-layer represents a specific object part. Our interpretable CNNs use the same training data as ordinary CNNs without a need for any annotations of object parts or textures for supervision. The interpretable CNN automatically assigns each filter in a high conv-layer with an object part during the learning process. We can apply our method to different types of CNNs with various structures. The explicit knowledge representation in an interpretable CNN can help people understand the logic inside a CNN, i.e. what patterns are memorized by the CNN for prediction. Experiments have shown that filters in an interpretable CNN are more semantically meaningful than those in a traditional CNN. The code is available at https://github.com/zqs1022/interpretableCNN.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00920