Research Article

Application Research for Fusion Model of Pseudolabel and Cross Network

Table 5

Experimental results of irregular hyperparameters values.

(, , , )Facial Beauty Prediction (%)(, , , )Facial Beauty Prediction (%)(, , , )Facial Beauty Prediction (%)

(0.1, 0.1, 0.1, 0.1)62.55(0.4, 0.1, 0.1, 0.4)62.55(0.7, 0.1, 0.1, 0.7)63.21
(0.1, 0.2, 0.2, 0.1)62.45(0.4, 0.2, 0.2, 0.4)64.11(0.7, 0.2, 0.2, 0.7)62.70
(0.1, 0.3, 0.3, 0.1)62.25(0.4, 0.3, 0.3, 0.4)63.00(0.7, 0.3, 0.3, 0.7)63.16
(0.1, 0.4, 0.4, 0.1)63.10(0.4, 0.4, 0.4, 0.4)64.76(0.7, 0.4, 0.4, 0.7)62.60
(0.1, 0.5, 0.5, 0.1)64.66(0.4, 0.5, 0.5, 0.4)63.20(0.7, 0.5, 0.5, 0.7)62.65
(0.1, 0.6, 0.6, 0.1)62.95(0.4, 0.6, 0.6, 0.4)62.35(0.7, 0.6, 0.6, 0.7)62.00
(0.1, 0.7, 0.7, 0.1)62.55(0.4, 0.7, 0.7, 0.4)62.60(0.7, 0.7, 0.7, 0.7)60.29
(0.1, 0.8, 0.8, 0.1)62.60(0.4, 0.8, 0.8, 0.4)(0.7, 0.8, 0.8, 0.7)
(0.1, 0.9, 0.9, 0.1)63.15(0.4, 0.9, 0.9, 0.4)62.10(0.7, 0.9, 0.9, 0.7)
(0.2, 0.1, 0.1, 0.2)62.15(0.5, 0.1, 0.1, 0.5)63.15(0.8, 0.1, 0.1, 0.8)62.50
(0.2, 0.2, 0.2, 0.2)62.55(0.5, 0.2, 0.2, 0.5)63.56(0.8, 0.2, 0.2, 0.8)62.55
(0.2, 0.3, 0.3, 0.2)62.42(0.5, 0.3, 0.3, 0.5)63.00(0.8, 0.3, 0.3, 0.8)63.20
(0.2, 0.4, 0.4, 0.2)62.85(0.5, 0.4, 0.4, 0.5)61.50(0.8, 0.4, 0.4, 0.8)63.30
(0.2, 0.5, 0.5, 0.2)62.70(0.5, 0.5, 0.5, 0.5)62.20(0.8, 0.5, 0.5, 0.8)
(0.2, 0.6, 0.6, 0.2)62.28(0.5, 0.6, 0.6, 0.5)63.15(0.8, 0.6, 0.6, 0.8)60.74
(0.2, 0.7, 0.7, 0.2)61.10(0.5, 0.7, 0.7, 0.5)62.80(0.8, 0.7, 0.7, 0.8)63.38
(0.2, 0.8, 0.8, 0.2)62.55(0.5, 0.8, 0.8, 0.5)62.85(0.8, 0.8, 0.8, 0.8)62.35
(0.2, 0.9, 0.9, 0.2)62.70(0.5, 0.9, 0.9, 0.5)61.24(0.8, 0.9, 0.9, 0.8)62.80
(0.3, 0.1, 0.1, 0.3)61.55(0.6, 0.1, 0.1, 0.6)63.05(0.9, 0.1, 0.1, 0.9)63.10
(0.3, 0.2, 0.2, 0.3)62.80(0.6, 0.2, 0.2, 0.6)62.75(0.9, 0.2, 0.2, 0.9)63.00
(0.3, 0.3, 0.3, 0.3)62.40(0.6, 0.3, 0.3, 0.6)63.26(0.9, 0.3, 0.3, 0.9)62.40
(0.3, 0.4, 0.4, 0.3)62.95(0.6, 0.4, 0.4, 0.6)62.60(0.9, 0.4, 0.4, 0.9)62.20
(0.3, 0.5, 0.5, 0.3)63.76(0.6, 0.5, 0.5, 0.6)63.20(0.9, 0.5, 0.5, 0.9)63.71
(0.3, 0.6, 0.6, 0.3)63.56(0.6, 0.6, 0.6, 0.6)62.68(0.9, 0.6, 0.6, 0.9)
(0.3, 0.7, 0.7, 0.3)62.32(0.6, 0.7, 0.7, 0.6)61.60(0.9, 0.7, 0.7, 0.9)
(0.3, 0.8, 0.8, 0.3)62.45(0.6, 0.8, 0.8, 0.6)(0.9, 0.8, 0.8, 0.9)62.39
(0.3, 0.9, 0.9, 0.3)62.30(0.6, 0.9, 0.9, 0.6)(0.9, 0.9, 0.9, 0.9)

Better results in terms of recognition rates were highlighted in bold.