Supplementary Material for " Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification "

This error may derive from two reasons. The first is that the classification branch of the model is not perfect, so the detector classifies a background region as a potted plant. The second is that the model classifier the region correctly, but regresses it to the wrong position. NMS cannot remove this kind of duplicate bounding box, resulting in an incorrect prediction. After uncertainty-aware soft target is adopted, the detector benefits from more certain regions during training.