Table 4.

Precision (Pre) and Recall (Rec) per class after fine-tuning the model for every target dataset. Precision and recall are computed, respectively, to their class.

Dataset	Bas		Eos		Ery		Lym		Mon		Neu
	Pre	Rec	Pre	Rec	Pre	Rec	Pre	Rec	Pre	Rec	Pre	Rec
Rabin	0.88	0.36	0.78	0.72			0.87	0.97	0.73	0.79	0.96	0.98
Munich 2021	0.64	0.13	0.75	0.80	0.78	0.93	0.76	0.88	0.91	0.28	0.89	0.96
Lisc	0.96	1.0	1.0	0.70			0.96	0.93	0.70	0.97	0.88	0.91
Jslh					1.00	1.00					1.00	1.00
Jin woo choi					1.0	0.87					0.72	1.0
Jiangxi tecom			0.58	1.0			0.80	0.60	0.88	0.85	0.96	0.97
Bccd			0.70	0.67			0.94	0.94	0.81	0.92	0.77	0.71
Tianjin	0.95	0.73	0.81	0.99			0.77	0.94	0.93	0.92	0.98	0.98