Improved Hard Example Mining Approach for Single Shot Object Detectors. (arXiv:2202.13080v2 [cs.CV] UPDATED)

Hard example mining methods generally improve the performance of the object
detectors, which suffer from imbalanced training sets. In this work, two
existing hard example mining approaches (LRM and focal loss, FL) are adapted
and combined in a state-of-the-art real-time object detector, YOLOv5. The
effectiveness of the proposed approach for improving the performance on hard
examples is extensively evaluated. The proposed method increases mAP by 3%
compared to using the original loss function and around 1-2% compared to using
the …

arxiv cv example mining