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).
[PDF]
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.
