Methods › General › Prioritized Sampling › IoU-Balanced Sampling

IoU-Balanced Sampling

6 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

IoU-Balanced Sampling is hard mining method for object detection. Suppose we need to sample N negative samples from M corresponding candidates. The selected probability for each sample under random sampling is:

p = N/M

To raise the selected probability of hard negatives, we evenly split the sampling interval into K bins according to IoU. N demanded negative samples are equally distributed to each bin. Then we select samples from them uniformly. Therefore, we get the selected probability under IoU-balanced sampling:

pₖ = N/K*1/Mₖ , k∈[0, K)

where Mₖ is the number of sampling candidates in the corresponding interval denoted by k. K is set to 3 by default in our experiments.

The sampled histogram with IoU-balanced sampling is shown by green color in the Figure to the right. The IoU-balanced sampling can guide the distribution of training samples close to the one of hard negatives.

Source: Libra R-CNN: Towards Balanced Learning for Object DetectionSee Code · OceanPang/Libra_R-CNN

Papers archive 2025-07-28

6 shown of 6, 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

10 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 Detection4
object-detection4
Ensemble Learning1
Fire Detection1
Fracture detection1
Management1
Medical Object Detection1
Object Localization1
Transfer Learning1
Weakly Supervised Object Detection1

Usage over time archive 2025-07-28

Papers per year tagged with IoU-Balanced Sampling: 2019 to 2024, peak 2 2 0 2019: 1 paper 2019 2020: 1 paper 2020 2021: 2 papers 2021 2022: 1 paper 2022 2023: 0 papers 2023 2024: 1 paper 2024
Papers per year the archive tags with this method, by the paper's archive date (6 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