Real Time Object Detection On Coco

评估指标

FPS (V100, b=1)

box AP

评测结果

各个模型在此基准测试上的表现结果

模型名称	FPS (V100, b=1)	box AP	Paper Title
YOLOv6-S6(1280)	98	50.3	YOLOv6 v3.0: A Full-Scale Reloading
PP-YOLOE+_L(distillation)	78	54.0	PP-YOLOE: An evolved version of YOLO
DEIM-D-FINE-X+	78 (T4)	-	DEIM: DETR with Improved Matching for Fast Convergence
PP-YOLOE+_M	-	49.8	PP-YOLOE: An evolved version of YOLO
PRB-FPN6-E-ELAN(1280)	31	56.9	Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection
YOLOv11m	212 (T4)	51.5	YOLOv11: An Overview of the Key Architectural Enhancements
YOLOR-E6	37	54.8	You Only Learn One Representation: Unified Network for Multiple Tasks
Faster RCNN-FPN+	26	42	End-to-End Object Detection with Transformers
RT-DETR-H(640)	40 (T4)	56.3	DETRs Beat YOLOs on Real-time Object Detection
YOLOv11l	161 (T4)	53.4	YOLOv11: An Overview of the Key Architectural Enhancements
MAFYOLOs	-	47.4	Multi-Branch Auxiliary Fusion YOLO with Re-parameterization Heterogeneous Convolutional for accurate object detection
DEIM-D-FINE-X+	78 (T4)	59.5	DEIM: DETR with Improved Matching for Fast Convergence
YOLOv10-X	-	54.4	YOLOv10: Real-Time End-to-End Object Detection
D-FINE-S+	287 (T4)	50.7	D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement
YOLOR-P6	49	52.6	You Only Learn One Representation: Unified Network for Multiple Tasks
YOLOR-W6	47	54.1	You Only Learn One Representation: Unified Network for Multiple Tasks
PRB-FPN-MSP	94	53.3	Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection
RT-DETR-L	114 (T4)	53.0	DETRs Beat YOLOs on Real-time Object Detection
YOLOv5-X	62.5	50.4	YOLOX: Exceeding YOLO Series in 2021
DAMO-YOLO-T	397	42	DAMO-YOLO : A Report on Real-Time Object Detection Design

0 of 82 row(s) selected.