YOLO-CORE: Contour Regression for Efficient Instance Segmentation
作者机构:School of Computer Science and Engineering and the Key Laboratory of Computer Network and Information Integration(Ministry of Education)Southeast UniversityNanjing 211189China
出 版 物:《Machine Intelligence Research》 (机器智能研究(英文版))
年 卷 期:2023年第20卷第5期
页 面:716-728页
核心收录:
学科分类:0831[工学-生物医学工程(可授工学、理学、医学学位)] 08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0714[理学-统计学(可授理学、经济学学位)] 0701[理学-数学] 0812[工学-计算机科学与技术(可授工学、理学学位)]
基 金:supported by the National Key R&D Program of China(Nos.2018AAA0100104 and 2018AAA0100100) Natural Science Foundation of Jiangsu Province,China(No.BK20211164).
主 题:Computer vision instance segmentation object shape prediction contour regression polar distance.
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 instance segmentation.The mask of the instance is efficiently acquired by explicit and direct contour regression using our designed multiorder 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).