Methods › Computer Vision › Proposal Filtering › Matrix NMS

Matrix Non-Maximum Suppression

Matrix NMS

5 papers tagged archive 2025-07-28

Introduced by Xinlong Wang et al. in SOLOv2: Dynamic and Fast Instance Segmentation

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

Matrix NMS, or Matrix Non-Maximum Suppression, performs non-maximum suppression with parallel matrix operations in one shot. It is motivated by Soft-NMS. Soft-NMS decays the other detection scores as a monotonic decreasing function f(iou) of their overlaps. By decaying the scores according to IoUs recursively, higher IoU detections will be eliminated with a minimum score threshold. However, such process is sequential like traditional Greedy NMS and can not be implemented in parallel.

Matrix NMS views this process from another perspective by considering how a predicted mask mⱼ being suppressed. For mⱼ, its decay factor is affected by: (a) The penalty of each prediction mᵢ on mⱼ (sᵢ>sⱼ), where sᵢ and sⱼ are the confidence scores; and (b) the probability of mᵢ being suppressed. For (a), the penalty of each prediction mᵢ on mⱼ could be easily computed by f(. iou ._(i, j)). For (b), the probability of mᵢ being suppressed is not so elegant to be computed. However, the probability usually has positive correlation with the IoUs. So here we directly approximate the probability by the most overlapped prediction on mᵢ as

f( iou. _(, i))=min_(∀sₖ>sᵢ) f( iou _(k, i))

To this end, the final decay factor becomes

decayⱼ=min_(∀sᵢ>sⱼ) (f( iou _(i, j)))/(f( iou _(·, i)))

and the updated score is computed by sⱼ=sⱼ · decay ⱼ . The authors consider the two most simple decremented functions, denoted as linear f(. iou ._(i, j))=1- iou _(i, j), and Gaussian f(. iou ._(i, j))=exp(-(i o u_(i, j)²)/σ).

PaperSource

Papers archive 2025-07-28

5 shown of 5, 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

15 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 Detection3
Object2
Real-Time Object Detection2
object-detection2
2D Object Detection1
Dense Object Detection1
Instance Segmentation1
Multi-Object Tracking1
Multiple Object Tracking1
Online Multi-Object Tracking1
Panoptic Segmentation1
Real-Time Semantic Segmentation1
Real-time Instance Segmentation1
Segmentation1
Semantic Segmentation1

Usage over time archive 2025-07-28

Papers per year tagged with Matrix NMS: 2020 to 2022, peak 2 2 0 2020: 2 papers 2020 2021: 1 paper 2021 2022: 2 papers 2022
Papers per year the archive tags with this method, by the paper's archive date (5 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

Proposal Filtering

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