본문 바로가기

Multi-Stage Instance Segmentation

문서 유형
연구출판물 · 학술대회 발표논문
등재
Scopus
저널 순위
Scopus Q4
저널
International Conference on ICT Convergence2022-October · pp.1803 · 2022
피인용
Scopus 0
FWCI (Scopus)
0
ISSN
2162-1233

저자

  1. 주 궈화제1저자Pusan National University, Department of Electronics Engineering, Busan, Republic of Korea
  2. 김석찬Pusan National University, Department of Electronics Engineering, Busan, Republic of Korea

초록

© 2022 IEEE.Two-stage instance segmentation relies on the correctness of the Region Proposal Network (RPN). To improve the accuracy of RPN, we propose a slight modification of the two-stage object detection network Faster R-CNN as a region proposal network. First, we remove the class branch of the second stage of Faster R-CNN and use the box regression as the output of the entire proposal network. Then we add a new box regression branch, classification branch, and segmentation branch as the final output. Finally, we train the entire network. The results show a great improvement in segmentation accuracy.

키워드

Faster R-CNNinstance segmentationRegion Proposal Network

식별자

Scopus EID
2-s2.0-85143254724