Aktivno učenje z mešanimi oznakami za detekcijo površinskih napak z globokimi nevronskimi mrežami

This paper investigates active learning strategies for mixed supervision in surface defect detection, where we search for a minimal set of samples selected for more accurate manual segmentation. We explore several approaches for sample selection based on entropy, margin sampling, and least confidence and apply them to a mixed supervision method, SegDecNet. We additionally explore extending active learning with probability calibration and equal sampling by categories to improve the robustness. Active learning approaches are evaluated on the KSDD2 dataset and compared against random sampling and a related purpose-built method for active learning in surface defect detection. We demonstrate that the least confidence method with the proposed extensions an outperform random sampling and other methods, achieving the same result as fully annotated dataset while requiring only a third of the fully annotated samples.