• Jun 03, 2019 News!Vol.9, No.5-Vol.10, No.3 have been indexed by EI (Inspec).   [Click]
  • Dec 31, 2020 News!Vol.13, No.1 has been published with online version.   [Click]
  • Nov 26, 2020 News!Vol.12, No.6 has been published with online version.   [Click]
General Information
Prof. Wael Badawy
Department of Computing and Information Systems Umm Al Qura University, Canada
I'm happy to take on the position of editor in chief of IJCTE. We encourage authors to submit papers concerning any branch of computer theory and engineering.
IJCTE 2018 Vol.10(6): 207-211 ISSN: 1793-8201
DOI: 10.7763/IJCTE.2018.V10.1227

Multi-scale Subnetwork for RoI Pooling for Instance Segmentation

Tran Duy Linh and Masayuki Arai
Abstract—Instance segmentation is a challenging task in computer vision because object locations in an image must be predicted and segmentation must be performed inside these locations. In the present paper, we propose a new pooling module to extract a small feature map from each Region of Interest for pixel-level prediction. Instead of using RoiAlign pooling, we use a small network module and ensemble the extracted multi-scale features in a feature map. The proposed method can output a better feature map and therefore better pixel-to-pixel alignment between input and output. The results of an experiment reveal that the proposed method outperforms cutting-edge instance segmentation methods.

Index Terms—Deep learning, instance segmentation, RoI pooling module.

Tran Duy Linh and Masayuki Arai are with Graduate School of Science and Engineering, Teikyo University, 1-1 Toyosatodai, Utsunomiya, Tochigi, Japan (email: arai@ics.teikyo-u.ac.jp).


Cite:Tran Duy Linh and Masayuki Arai, "Multi-scale Subnetwork for RoI Pooling for Instance Segmentation," International Journal of Computer Theory and Engineering vol. 10, no. 6, pp. 207-211, 2018.

Copyright © 2008-2021. International Association of Computer Science and Information Technology. All rights reserved.