# A convnet for non-maximum suppression

arXiv: https://arxiv.org/abs/1511.06437 · HTML: https://mlsanity.com/paper/1511.06437/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2015.

## Built on by (most cited first, 9 of 9)

- [GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.17202/) (2021)
- [Progressive End-to-End Object Detection in Crowded Scenes](https://mlsanity.com/paper/2203.07669/) (2022)
- [CBARF: Cascaded Bundle-Adjusting Neural Radiance Fields from Imperfect Camera Poses](https://mlsanity.com/paper/2310.09776/) (2023)
- [Beta R-CNN: Looking into Pedestrian Detection from Another Perspective](https://mlsanity.com/paper/2210.12758/) (2022)
- [A Curated and Re-annotated Peripheral Blood Cell Dataset Integrating Four Public Resources](https://mlsanity.com/paper/2407.13214/) (2024)
- [PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery](https://mlsanity.com/paper/2105.12990/) (2021)
- [From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks](https://mlsanity.com/paper/2405.06038/) (2024)
- [Density-based Object Detection in Crowded Scenes](https://mlsanity.com/paper/2504.09819/) (2025)
- [Inverted Non-maximum Suppression for more Accurate and Neater Face Detection](https://mlsanity.com/paper/2305.10593/) (2023)

## Abstract (arXiv)

Non-maximum suppression (NMS) is used in virtually all state-of-the-art object detection pipelines. While essential object detection ingredients such as features, classifiers, and proposal methods have been extensively researched surprisingly little work has aimed to systematically address NMS. The de-facto standard for NMS is based on greedy clustering with a fixed distance threshold, which forces to trade-off recall versus precision. We propose a convnet designed to perform NMS of a given set of detections. We report experiments on a synthetic setup, and results on crowded pedestrian detection scenes. Our approach overcomes the intrinsic limitations of greedy NMS, obtaining better recall and precision.