Dilated convolutions for image classification and object localization

Yasunori Kudo, Yoshimitsu Aoki

    研究成果: Conference contribution

    15 被引用数 (Scopus)

    抄録

    Yu et al.[1] showed that dilated convolutions are very effective in dense prediction problems such as semantic segmentation. In this work, we propose a new ResNet[2] based convolutional neural network model using dilated convolutions and show that this model can achieve lower error rate for image classification than ResNet with reduction of the number of the parameters of the network by 94% and that this model has high ability to localize objects despite being trained on image-level labels. We evaluated this model on ImageNet[5] which has 50 class labels randomly selected from 1000 class labels.

    本文言語English
    ホスト出版物のタイトルProceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017
    出版社Institute of Electrical and Electronics Engineers Inc.
    ページ452-455
    ページ数4
    ISBN(電子版)9784901122160
    DOI
    出版ステータスPublished - 2017 7 19
    イベント15th IAPR International Conference on Machine Vision Applications, MVA 2017 - Nagoya, Japan
    継続期間: 2017 5 82017 5 12

    Other

    Other15th IAPR International Conference on Machine Vision Applications, MVA 2017
    国/地域Japan
    CityNagoya
    Period17/5/817/5/12

    ASJC Scopus subject areas

    • 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

    「Dilated convolutions for image classification and object localization」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