Table 5 Stage 2: Comparative experiment of different data augmentation algorithms.

From: Research on pedestrian recognition in complex scenarios based on data augmentation using large language models

Models

Params/M

GFLOPs

P/%

R/%

mAP@0.5/%

mAP@0.5:0.95/%

YOLOv8n (baseline)

11.17

28.8

87.2

80.8

89.7

63.8

YOLOv10n

8.0

24.4

87.2

81.4

89.8

63.6

YOLOv11n

2.6

6.3

87.4

80.4

89.5

63.7

YOLOv12n

2.6

6.3

87.7

82.7

90.6

65

REG-YOLO (Ours)

7.91

21.2

87.9

83.5

90.7

65.5

  1. The optimal result in the experimental comparison is shown in bold.
Back to article page