Improving the efficiency of steel plate surface defect classification by reducing the labelling cost using deep active learning

URN:NBN:SI:doc-DFKQLRJQ2024Gong, TianyuLi, YuzeMeng, GaoleiYang, WenjiaZhou, Youhangdocuments/doc/D/URN_NBN_SI_doc-DFKQLRJQ_001.pdfdocuments/doc/D/URN_NBN_SI_doc-DFKQLRJQ_001.txt11/1270articlestr. 554-56810.5545/sv-jme.2023.9002237990432536-3948URN:NBN:SI:doc-DFKQLRJQengFakulteta za strojništvoStrojniški vestnikInCactive learningaktivno učenjeconvolutional neural networkglobal poolingglobalno združevanjeklasifikacija površinskih napakkonvolucijska nevronska mrežasurface defect classificationImproving the efficiency of steel plate surface defect classification by reducing the labelling cost using deep active learning