An Improved Self-Training Model with Fine-Tuning Teacher/Student Exchange Strategy to Detect Computer-Generated Images

Table 5

Average results of three experiments.

Model	Accuracy (%)	Precision (%)	Recall (%)
M0	94.79	93.70	96.05
M1	94.89	93.57	96.29
M2	94.82	93.30	96.29
M3	95.09	93.95	96.39