Table 6 Stage 2: Comparative experiments of different algorithms following data augmentation in complex scenarios.

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)

3.0

8.1

87.7

76.4

87

59.5

YOLOv10n

2.6

8.2

88.7

78.8

87.3

60.4

YOLOv11n

2.5

6.3

88.5

78.5

89.3

63.3

YOLOv12n

2.6

6.3

89.9

81.2

89.2

65

REG-YOLO (Ours)

2.2

6.4

91.6

81

89.6

64.7

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