Table 3.

Comparison of Average Precision (AP) on the NEU-DET dataset. The best results are shown in boldface.

AP	Defect
	Inclusion (In)	Patches (Pa)	Pitted Surface (Ps)	Scratches (Sc)	mAP	Data (%)
Random	0.5498	0.7498	0.3082	0.5658	0.542	50.0%
EN	0.6359	0.8314	0.1959	0.8546	0.629	31.6%
MS	0.6874	0.7944	0.1763	0.9104	0.642	33.3%
Full	0.6183	0.7284	0.2103	0.7720	0.582	100%
Ours	0.6390	0.8269	0.3277	0.7874	0.645	21.7%