Realtime single-stage instance segmentation network based on anchors. (October 2021)

• Record Type: Journal Article
• Authors: Cai, Jintong; Li, Yujie
• Is Part Of: Computers & electrical engineering. Volume 95(2021)
• Publication Date: 2021-10
• Subjects: Instance segmentation -- One-stage -- Mask -- Anchors; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107464
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Propose an instance segmentation method uses a single-stage detector. Set anchors of different sizes on multi-scale feature maps. Disassemble the instance segmentation task into two parallel branches, and finally obtain the mask through simple linear combination. Get 35.12fps on a single NVIDIA GEFORCE GTX 2080 GPU. Abstract: In this paper, we propose an instance segmentation method uses a single-stage detector. Compared to the two-stage method, the single-stage method is simpler and easier to train. Not rely on the traditional region proposal, it directly uses pixels, which reduces the complexity of the network and significantly increases the speed. Our segmentation method is based on anchor boxes, which performs multi-scale detection by setting anchors of different sizes on multi-scale feature maps. We add a new branch to the prediction head to generate prototype masks and mask coefficients, then linearly combine them to generate mask. In our experiments, the proposed model had better performance, we got 35.12 fps on a single NVIDIA GEFORCE GTX 2080 GPU, which proves that our method is simple, effective, and faster. Graphical abstract: Image, graphical abstract