Table 6 Comparison of model complexity and inference efficiency. The inference speed (FPS) is measured on an NVIDIA GeForce RTX 4080 GPU.

From: ScaleMamba-YOLO: a multi-scale MambaYOLO for medical object detection

Model

Params (M)

FLOPs (G)

FPS

Inference Time (ms)

FASTER RCNN33

41.35

180.0

22

45.0

DINO18

47.54

220.0

18

55.0

RT-DETR20

41.94

125.6

73

13.6

YOLOv834

2.54

6.8

242

4.2

YOLOv935

2.69

7.6

111

8.9

YOLOv1036

2.58

8.2

249

4.1

YOLOv1137

2.56

6.3

243

4.1

MambaYOLO30

5.98

13.6

139

7.2

ScaleMamba-YOLO

7.82

17.0

110

9.1

Back to article page