YOLO-CORE: Contour Regression for Efficient Instance Segmentation  

作　　者：Haoliang Liu Wei Xiong Yu Zhang 

机构地区：[1]School of Computer Science and Engineering and the Key Laboratory of Computer Network and Information Integration(Ministry of Education),Southeast University,Nanjing 211189,China

出　　处：《Machine Intelligence Research》2023年第5期716-728,共13页机器智能研究（英文版）

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).

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).

关 键 词：Computer vision instance segmentation object shape prediction contour regression polar distance. 

分 类 号：R318[医药卫生—生物医学工程] TP391.41[医药卫生—基础医学]