[Papers] Interpretable Convolutional Neural Network Including Attribute Estimation for Image Classification

• Horii Kazaha

  Graduate School of Information Science and Technology, Hokkaido University

• Maeda Keisuke

  Faculty of Information Science and Technology, Hokkaido University

• Ogawa Takahiro

  Faculty of Information Science and Technology, Hokkaido University

• Haseyama Miki

  Faculty of Information Science and Technology, Hokkaido University

抄録

An interpretable convolutional neural network (CNN) including attribute estimation for image classification is presented in this paper. Although CNNs perform highly accurate image classification, the reason for the classification results obtained by the neural networks is not clear. In order to provide interpretation of CNNs, the proposed method estimates attributes, which explain elements of objects, in an intermediate layer of the network. This enables improvement of the interpretability of CNNs, and it is the main contribution of this paper. Furthermore, the proposed method uses the estimated attributes for image classification in order to enhance its accuracy. Consequently, the proposed method not only provides interpretation of CNNs but also realizes improvement in the performance of image classification.

収録刊行物

• 映像情報メディア学会英語論文誌

  映像情報メディア学会英語論文誌 8 (2), 111-124, 2020

  一般社団法人 映像情報メディア学会

キーワード

• Interpretable convolutional neural network
• attribute estimation
• image classification

詳細情報

• CRID: 1390565134844445952
• NII論文ID: 130007825882
• DOI: 10.3169/mta.8.111
• ISSN: 21867364
• Web Site: https://www.jstage.jst.go.jp/article/mta/8/2/8_111/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可