Papers › Training Region-based Object Detectors with Online Hard Example Mining

Training Region-based Object Detectors with Online Hard Example Mining

12 Apr 2016CVPR 2016 6arXiv:1604.03540archive 2025-07-28

Abhinav Shrivastava, Abhinav Gupta, Ross Girshick

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Bennie-Han/Image-augementation-pytorch mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report
abhi2610/ohem mentioned on GitHubcaffe2NOASSERTION report
hh-xiaohu/Image-augementation-pytorch mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Identification Trillion Pairs Dataset HM-Softmax Accuracy 36.75 #6 of 6 Archive leaderboard report
Face Verification Trillion Pairs Dataset HM-Softmax Accuracy 34.46 #6 of 6 Archive leaderboard report
Object Detection PASCAL VOC 2007 OHEM MAP 78.9% #14 of 30 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: OHEM

OHEM

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections