Table 5.

Experimental evaluation of the algorithm with AugMix augmentation and JS Loss (cross-domain Re-ID). Symbols: M—Market-1501; D—DukeMTMC-reID; MSMT17 Merged—MSMT17, which combines training and test parts.

Algorithm	MSMT17 Merged → M		MSMT17 Merged → D
	${\mathit{Rank}}_{\mathbf{1}}\mathbf{(}\mathbf{\uparrow }\mathbf{)}\mathbf{,}\mathbf{\%}$	$\mathit{mAP}\mathbf{(}\mathbf{\uparrow }\mathbf{)}\mathbf{,}\%$	${\mathit{Rank}}_{\mathbf{1}}\mathbf{(}\mathbf{\uparrow }\mathbf{)}\mathbf{,}\mathbf{\%}$	$\mathit{mAP}\mathbf{(}\mathbf{\uparrow }\mathbf{)}\mathbf{,}\mathbf{\%}$
Baseline	65.65	37.71	66.16	47.74
+Res2Net50	69.74	41.32	70.65	52.37
+AugMix and JS Loss	71.08	43.39	72.51	53.71

The best results by metrics are highlighted in bold.