YOLO-CORE: Contour Regression for Efficient Instance Segmentation

doi:10.1007/s11633-022-1379-3

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > International Journal of Automation and Computing

	YOLO-CORE: Contour Regression for Efficient Instance Segmentation
	Haoliang Liu, Wei Xiong, Yu Zhang
刊名	Machine Intelligence Research
	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
DOI	10.1007/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).
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/52447]
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, Wei Xiong, Yu Zhang."YOLO-CORE: Contour Regression for Efficient Instance Segmentation".Machine Intelligence Research 20.5(2023):716-728.