Methods › General › Prioritized Sampling › OHEM

Online Hard Example Mining

OHEM

8 papers tagged archive 2025-07-28

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.

PaperSourceSee Code · abhi2610/ohem

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.

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.

TaskPapers
Object Detection6
object-detection6
Object5
Diversity1
Image Classification1
Instance Segmentation1
Interactive Segmentation1
Lesion Detection1
Multi-Task Learning1
Segmentation1
Semantic Segmentation1
Triplet1
Video Object Segmentation1
image-classification1

Usage over time archive 2025-07-28

Papers per year tagged with OHEM: 2016 to 2025, peak 3 3 0 2016: 1 paper 2016 2017: 3 papers 2017 2018: 0 papers 2018 2019: 2 papers 2019 2020: 0 papers 2020 2021: 0 papers 2021 2022: 0 papers 2022 2023: 1 paper 2023 2024: 0 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (8 dated). Bars are counts, not a trend claim.

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

Prioritized Sampling

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