{"type":"ScholarlyArticle","title":"Interpretable Compositional Convolutional Neural Networks","authors":[{"name":"Wen Shen","slug":"wen-shen","given":"Wen","family":"Shen","affiliation":""},{"name":"Zhihua Wei","slug":"zhihua-wei","given":"Zhihua","family":"Wei","affiliation":""},{"name":"Shikun Huang","slug":"shikun-huang","given":"Shikun","family":"Huang","affiliation":""},{"name":"Binbin Zhang","slug":"binbin-zhang","given":"Binbin","family":"Zhang","affiliation":""},{"name":"Jiaqi Fan","slug":"jiaqi-fan","given":"Jiaqi","family":"Fan","affiliation":""},{"name":"Ping Zhao","slug":"ping-zhao","given":"Ping","family":"Zhao","affiliation":""},{"name":"Quanshi Zhang","slug":"quanshi-zhang","given":"Quanshi","family":"Zhang","affiliation":""}],"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.","doi":"10.24963/ijcai.2021/409","url":"https://ijcai.org/proceedings/2021/409","pdf":"https://ijcai.org/proceedings/2021/0409.pdf","markdown":"https://ijcai.org/proceedings/2021/409.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/409","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Machine Learning","track":"Main Track","number":409,"pages":{"first":2971,"last":2978},"keywords":["AI Ethics, Trust, Fairness: Explainability","Machine Learning: Explainable/Interpretable Machine Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}