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

Table 6

Benchmark test results.

Model	Accuracy (%)	Precision (%)	Recall (%)
M0	83.42	87.76	80.74
M1	87.83	90.91	85.62
M2	88.54	91.30	86.51
M3	88.60	91.62	86.39