Table 4.

Experimental comparison of the VeRi776 dataset.

Models	mAP (%)	rank−1 (%)	rank−5 (%)
LOMO (Liao et al., 2015)	9.64	25.33	46.48
DGD (Xiao et al., 2016)	17.92	50.70	67.52
GoogLeNet (Yang et al., 2015)	17.81	52.12	66.79
FACT (Liu et al., 2016b)	18.73	51.85	67.16
Siamese Visual (Shen et al., 2017)	29.48	41.12	60.31
PAMAL (Tumrani et al., 2020)	45.06	-	-
MSCL (Yuefeng et al., 2022)	45.90	81.20	-
OIFE (Wang et al., 2017)	48.00	65.92	87.66
VAMI (Zhu et al., 2017)	50.13	77.03	90.82
QD-DFL (Zhu et al., 2020)	51.83	88.50	94.46
VRSDnet (Zhu et al., 2019)	53.45	83.49	92.55
FDA-Net (Lou et al., 2019a)	53.46	84.27	92.43
MV-GAN (Zhang et al., 2021)	61.16	91.06	95.77
VAAG (Tumrani et al., 2023)	63.01	92.20	96.64
VPEN (Meng et al., 2020)	67.98	90.36	94.84
VehicleNet (Zheng et al., 2021)	67.48	90.58	95.47
UFC (Wang et al., 2021)	68.24	91.84	96.73
CTCAL (Yu et al., 2021)	68.65	90.46	95.97
Ours	68.83	92.94	96.88