---
title: "Interpretable Compositional Convolutional Neural Networks"
authors:
  - "Wen Shen"
  - "Zhihua Wei"
  - "Shikun Huang"
  - "Binbin Zhang"
  - "Jiaqi Fan"
  - "Ping Zhao"
  - "Quanshi Zhang"
doi: "10.24963/ijcai.2021/409"
url: "https://ijcai.org/proceedings/2021/409"
pdf: "https://ijcai.org/proceedings/2021/0409.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "2971-2978"
track: "Main Track"
keywords:
  - "AI Ethics, Trust, Fairness: Explainability"
  - "Machine Learning: Explainable/Interpretable Machine Learning"
---

# Interpretable Compositional Convolutional Neural Networks

Wen Shen, Zhihua Wei, Shikun Huang, Binbin Zhang, Jiaqi Fan, Ping Zhao, Quanshi Zhang

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 2971-2978. DOI: [10.24963/ijcai.2021/409](https://doi.org/10.24963/ijcai.2021/409)

## Abstract

This paper proposes a method to modify a traditional convolutional neural network (CNN) into an interpretable compositional CNN, in order to learn filters that encode meaningful visual patterns in intermediate convolutional layers. In a compositional CNN, each filter is supposed to consistently represent a specific compositional object part or image region with a clear meaning. The compositional CNN learns from image labels for classification without any annotations of parts or regions for supervision. Our method can be broadly applied to different types of CNNs. Experiments have demonstrated the effectiveness of our method. The code will be released when the paper is accepted.