中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
YOLO-CORE: Contour Regression for Efficient Instance Segmentation

文献类型:期刊论文

作者Haoliang Liu; Wei Xiong; Yu Zhang
刊名Machine Intelligence Research
出版日期2023
卷号20期号:5页码:716-728
关键词Computer vision, instance segmentation, object shape prediction, contour regression, polar distance
ISSN号2731-538X
DOI10.1007/s11633-022-1379-3
英文摘要Instance segmentation has drawn mounting attention due to its significant utility. However, high computational costs have been widely acknowledged in this domain, as the instance mask is generally achieved by pixel-level labeling. In this paper, we present a conceptually efficient contour regression network based on the you only look once (YOLO) architecture named YOLO-CORE for in stance segmentation. The mask of the instance is efficiently acquired by explicit and direct contour regression using our designed multi order constraint consisting of a polar distance loss and a sector loss. Our proposed YOLO-CORE yields impressive segmentation performance in terms of both accuracy and speed. It achieves 57.9% AP@0.5 with 47 FPS (frames per second) on the semantic boundaries dataset (SBD) and 51.1% AP@0.5 with 46 FPS on the COCO dataset. The superior performance achieved by our method with explicit contour regression suggests a new technique line in the YOLO-based image understanding field. Moreover, our instance segmentation design can be flexibly integrated into existing deep detectors with negligible computation cost (65.86 BFLOPs (billion float operations per second) to 66.15 BFLOPs with the YOLOv3 detector).
源URL[http://ir.ia.ac.cn/handle/173211/56006]  
专题自动化研究所_学术期刊_International Journal of Automation and Computing
作者单位School of Computer Science and Engineering and the Key Laboratory of Computer Network and Information Integration (Ministry of Education), Southeast University, Nanjing 211189, China
推荐引用方式
GB/T 7714
Haoliang Liu,Wei Xiong,Yu Zhang. YOLO-CORE: Contour Regression for Efficient Instance Segmentation[J]. Machine Intelligence Research,2023,20(5):716-728.
APA Haoliang Liu,Wei Xiong,&Yu Zhang.(2023).YOLO-CORE: Contour Regression for Efficient Instance Segmentation.Machine Intelligence Research,20(5),716-728.
MLA Haoliang Liu,et al."YOLO-CORE: Contour Regression for Efficient Instance Segmentation".Machine Intelligence Research 20.5(2023):716-728.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。