Methods › General › Prioritized Sampling › OHEM
Online Hard Example Mining
OHEM
Introduced by Abhinav Shrivastava et al. in Training Region-based Object Detectors with Online Hard Example Mining
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Some object 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, or Online Hard Example Mining, is a bootstrapping technique that modifies SGD to sample from examples in a non-uniform way depending on the current loss of each example under consideration. The method takes advantage of detection-specific problem structure in which each SGD mini-batch consists of only one or two images, but thousands of candidate examples. The candidate examples are subsampled according to a distribution that favors diverse, high loss instances.
Papers archive 2025-07-28
8 shown of 8, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality images 24 May 2025 · 0 repositories · arXiv:2505.18741
-
A systematic study of the foreground-background imbalance problem in deep learning for object detection 28 Jun 2023 · 0 repositories · arXiv:2306.16539
-
Prime Sample Attention in Object Detection 9 Apr 2019 · 1 repository · arXiv:1904.04821
-
ThunderNet: Towards Real-time Generic Object Detection 28 Mar 2019 · 3 repositories · arXiv:1903.11752
-
Deep Extreme Cut: From Extreme Points to Object Segmentation 24 Nov 2017 · 2 repositories · arXiv:1711.09081
-
S-OHEM: Stratified Online Hard Example Mining for Object Detection 5 May 2017 · 0 repositories · arXiv:1705.02233
-
Improving Object Detection with Region Similarity Learning 1 Mar 2017 · 0 repositories · arXiv:1703.00234
-
Training Region-based Object Detectors with Online Hard Example Mining 12 Apr 2016 · 5 repositories · arXiv:1604.03540
Tasks archive 2025-07-28
14 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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