Explaining convolutional neural networks using softmax gradient layer-wise relevance propagation

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

4 被引用数 (Scopus)

抄録

Convolutional Neural Networks (CNN) have become state-of-the-art in the field of image classification. However, not everything is understood about their inner representations. This paper tackles the interpretability and explainability of the predictions of CNNs for multi-class classification problems. Specifically, we propose a novel visualization method of pixel-wise input attribution called Softmax-Gradient Layer-wise Relevance Propagation (SGLRP). The proposed model is a class discriminate extension to Deep Taylor Decomposition (DTD) using the gradient of softmax to back propagate the relevance of the output probability to the input image. Through qualitative and quantitative analysis, we demonstrate that SGLRP can successfully localize and attribute the regions on input images which contribute to a target object's classification. We show that the proposed method excels at discriminating the target objects class from the other possible objects in the images. We confirm that SGLRP performs better than existing Layer-wise Relevance Propagation (LRP) based methods and can help in the understanding of the decision process of CNNs.

本文言語英語
ホスト出版物のタイトルProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
出版社Institute of Electrical and Electronics Engineers Inc.
ページ4176-4185
ページ数10
ISBN(電子版)9781728150239
DOI
出版ステータス出版済み - 10 2019
イベント17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, 大韓民国
継続期間: 10 27 201910 28 2019

出版物シリーズ

名前Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

会議

会議17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
国/地域大韓民国
CitySeoul
Period10/27/1910/28/19

All Science Journal Classification (ASJC) codes

  • コンピュータ サイエンスの応用
  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Explaining convolutional neural networks using softmax gradient layer-wise relevance propagation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル