arrow
返回

Attention-based adaptive context network for anchor-free instance segmentation

delete2022-09-15
delete1
PRE
AI
T
Tong Zhang
张国山 封面图
张国山 (Guoshan Zhang) *
M
Min Yan
Y
Yueming Zhang
DOI:10.1007/s13042-022-01648-xdelete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
It is crucial to obtain accurate and efficient instance segmentation masks in many modern applications such as automatic pilot and robotic manipulation. In this paper, we propose a straightforward and flexible two-stage framework for instance segmentation, which simultaneously generates box-level localization information in an image and instance-level segmentation information for each instance. We name this framework as Attention-based Adaptive Context Network for anchor-free Instance Segmentation (ContextMask), which extends the object detector FCOS (Fully Convolutional One-stage Object Detection) by adding a novel multi-scale adaptive context-guided mask (MACG-Mask) branch containing an adaptive context network and a MaskloU branch. The adaptive context network is to combine the global context in predicted bounding boxes and the MaskloU branch is to evaluate the quality of the predicted masks. With the development of deep convolutional neural networks, the network continues to deepen so that it is difficult to balance spatial information and semantic information well. To address the issue, we design a weighted FPN, which obtains feature maps with balance-well spatial and semantic information by concatenating and weighting feature maps of different resolutions. Besides, we also propose an attention-based head, which adds spatial attention and channel attention module to make each pixel have a unique weight to solve the problem of large-scale variant of objects. We verify ContextMask's effectiveness on the fine-annotations Cityscapes and COCO dataset. ContextMask outperforms state-of-the-art methods and achieves 38.4% AP on the Cityscapes dataset and 39.0%AP on the COCO dataset.
Keyword:
Instance segmentation
MACG-mask branch
Weighted FPN
ContextMask

期刊

International Journal of Machine Learning and Cybernetics 封面图
International Journal of Machine Learning and Cybernetics
IF:
2.7
论文数:
3.2K
被引数:
5.6K

机构

T
tianjin university
学者数:
8.0W
论文数: 5.8W
被引数: 88
引用论文

引用论文

A Pilot Study of the Efficacy of the Unified Protocol for Transdiagnostic Treatment of Emotional Disorders in Treating Posttraumatic Psychopathology: A Randomized Controlled Trial
err2021-01-16
err0
errOAAI
errMeaghan L. O'Donnell; Winnie Lau; Katherine Chisholm; James Agathos; Jonathon Little; Sonia Terhaag; Rachel Brand; Andrea Putica; Alexander C. N. Holmes; Lynda Katona; Kim L. Felmingham; Kim Murray; Fardous Hosseiny; Matthew W. Gallagher
err分享
err收藏
A Monte Carlo model of irradiation-induced recrystallization in polycrystalline UMo fuels
err2019-10-01
err0
errOAAI
errWilliam E. Frazier; Shenyang Hu; Douglas E. Burkes; Benjamin W. Beeler
err分享
err收藏
err分享
err收藏
学者 查看更多内容