Table 3.

Comparison of variant models and our model.

Model	Attention module	mAP	FPS	Batch size	Input resolution
YOLOv5	Baseline	0.6674	151	2	608 × 608
Our model	CGAN	0.6791	116	2	512 × 512
Our model	CVAE	0.6825	147	2	512 × 512
Our model	CVAE-GAN	0.6837	108	2	512 × 512

The bold values were used to label the best performing score compared with others.