PP-YOLO: An Effective and Efficient Implementation of Object Detector

23 Jul 2020Xiang LongKaipeng DengGuanzhong WangYang ZhangQingqing DangYuan GaoHui ShenJianguo RenShumin HanErrui DingShilei Wen

Object detection is one of the most important areas in computer vision, which plays a key role in various practical scenarios. Due to limitation of hardware, it is often necessary to sacrifice accuracy to ensure the infer speed of the detector in practice... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Object Detection COCO test-dev PP-YOLO (608x608) box AP 45.2 # 28
AP50 65.2 # 27
AP75 49.9 # 31
APS 26.3 # 37
APM 47.8 # 32
APL 57.2 # 31
Object Detection COCO test-dev PP-YOLO (320x320) box AP 39.3 # 60
AP50 59.3 # 60
AP75 42.7 # 65
APS 16.7 # 75
APM 41.4 # 63
APL 57.8 # 27

Methods used in the Paper