Training Region-Based Object Detectors with Online Hard Example Mining
- 1 June 2016
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 761-769
- https://doi.org/10.1109/cvpr.2016.89
Abstract
The field of object detection has made significant 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 efficient. OHEM is a simple and intuitive algorithm that eliminates several heuristics and hyperparameters in common use. But more importantly, it yields consistent and significant boosts in detection performance on benchmarks like PASCAL VOC 2007 and 2012. Its effectiveness increases as datasets become larger and more difficult, as demonstrated by the results on the MS COCO dataset. Moreover, combined with complementary advances in the field, OHEM leads to state-of-the-art results of 78.9% and 76.3% mAP on PASCAL VOC 2007 and 2012 respectively.Keywords
This publication has 17 references indexed in Scilit:
- Fast R-CNNPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Unsupervised Learning of Visual Representations Using VideosPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Object Detection via a Multi-region and Semantic Segmentation-Aware CNN ModelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Multiscale Combinatorial GroupingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- BING: Binarized Normed Gradients for Objectness Estimation at 300fpsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Constrained parametric min-cuts for automatic object segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009