Abstract
The fifield of object detection has made signifificant advances riding on the wave of region-based ConvNets, but their training procedure still includes many heuristics and hyperparameters that are costly to tune. We present a simple yet surprisingly effective online hard example mining (OHEM) algorithm for training region-based ConvNet detectors. Our motivation is the same as it has always been – detection datasets contain an overwhelming number of easy examples and a small number of hard examples. Automatic selection of these hard examples can make training more effective and effificient. OHEM is a simple and intuitive algorithm that eliminates several heuristics and hyperparameters in common use. But more importantly, it yields consistent and signifificant boosts in detection performance on benchmarks like PASCAL VOC 2007 and 2012. Its effectiveness increases as datasets become larger and more diffificult, as demonstrated by the results on the MS COCO dataset. Moreover, combined with complementary advances in the fifield, OHEM leads to state-of-the-art results of 78.9% and 76.3% mAP on PASCAL VOC 2007 and 2012 respectively