Superpixel convolution for segmentation

Teppei Suzuki, Shuichi Akizuki, Naoki Kato, Yoshimitsu Aoki

研究成果: Conference contribution

4 被引用数 (Scopus)

抄録

In this paper, we propose a novel segmentation algorithm based on convolutional neural networks (CNNs) on superpix-else CNNs are powerful methods for several computer vision tasks, but spatial information disappears through the pooling process. Moreover, since pooling compresses different types of pixels into a single value, pooling sometimes negatively affects the results of inference in segmentation task. We use superpixel pooling instead of general pooling to resolve this problem. However, general CNNs can't use superpixel images in which the adjacency relationships between pixels are broken. Therefore, we define CNNs and Dilated Convolution on superpixels. Finally, we show the effectiveness of proposed method on an HKU-IS dataset.

本文言語English
ホスト出版物のタイトル2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
出版社IEEE Computer Society
ページ3249-3253
ページ数5
ISBN(電子版)9781479970612
DOI
出版ステータスPublished - 2018 8月 29
イベント25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
継続期間: 2018 10月 72018 10月 10

出版物シリーズ

名前Proceedings - International Conference on Image Processing, ICIP
ISSN(印刷版)1522-4880

Conference

Conference25th IEEE International Conference on Image Processing, ICIP 2018
国/地域Greece
CityAthens
Period18/10/718/10/10

ASJC Scopus subject areas

  • ソフトウェア
  • コンピュータ ビジョンおよびパターン認識
  • 信号処理

フィンガープリント

「Superpixel convolution for segmentation」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