# Learning non-maximum suppression

arXiv: https://arxiv.org/abs/1705.02950 · HTML: https://mlsanity.com/paper/1705.02950/

## Key facts

- Cited by 113 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2017.

## Built on by (most cited first, 30 of 113)

- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment](https://mlsanity.com/paper/2207.13085/) (2022)
- [Real-Time Flying Object Detection with YOLOv8](https://mlsanity.com/paper/2305.09972/) (2023)
- [Multimodal Object Detection via Probabilistic Ensembling](https://mlsanity.com/paper/2104.02904/) (2021)
- [Differentiable Patch Selection for Image Recognition](https://mlsanity.com/paper/2104.03059/) (2021)
- [GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.17202/) (2021)
- [Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)](https://mlsanity.com/paper/2108.05888/) (2021)
- [SODFormer: Streaming Object Detection with Transformer Using Events and Frames](https://mlsanity.com/paper/2308.04047/) (2023)
- [Learnable Online Graph Representations for 3D Multi-Object Tracking](https://mlsanity.com/paper/2104.11747/) (2021)
- [LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection](https://mlsanity.com/paper/2406.03459/) (2024)
- [ADA-Track++: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association](https://mlsanity.com/paper/2405.08909/) (2024)
- [Progressive End-to-End Object Detection in Crowded Scenes](https://mlsanity.com/paper/2203.07669/) (2022)
- [Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardware](https://mlsanity.com/paper/2312.00425/) (2023)
- [Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation](https://mlsanity.com/paper/2308.07313/) (2023)
- [Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models](https://mlsanity.com/paper/2403.07304/) (2024)
- [FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering](https://mlsanity.com/paper/2506.21710/) (2025)
- [A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask Inpainting](https://mlsanity.com/paper/2401.10227/) (2024)
- [T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression](https://mlsanity.com/paper/2109.10948/) (2021)
- [MVG-Splatting: Multi-View Guided Gaussian Splatting with Adaptive Quantile-Based Geometric Consistency Densification](https://mlsanity.com/paper/2407.11840/) (2024)
- [Boosting Detection in Crowd Analysis via Underutilized Output Features](https://mlsanity.com/paper/2308.16187/) (2023)
- [ODAM: Gradient-based instance-specific visual explanations for object detection](https://mlsanity.com/paper/2304.06354/) (2023)
- [RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity](https://mlsanity.com/paper/2504.13099/) (2025)
- [CBARF: Cascaded Bundle-Adjusting Neural Radiance Fields from Imperfect Camera Poses](https://mlsanity.com/paper/2310.09776/) (2023)
- [Variational Pedestrian Detection](https://mlsanity.com/paper/2104.12389/) (2021)
- [Towards Balanced Learning for Instance Recognition](https://mlsanity.com/paper/2108.10175/) (2021)
- [Planning from Imagination: Episodic Simulation and Episodic Memory for Vision-and-Language Navigation](https://mlsanity.com/paper/2412.01857/) (2024)
- [Graph Fusion Network for Multi-Oriented Object Detection](https://mlsanity.com/paper/2205.03562/) (2022)
- [A Mask Attention Interaction and Scale Enhancement Network for SAR Ship Instance Segmentation](https://mlsanity.com/paper/2207.03912/) (2022)
- [Real-time object detection and robotic manipulation for agriculture using a YOLO-based learning approach](https://mlsanity.com/paper/2401.15785/) (2024)

## Abstract (arXiv)

Object detectors have hugely profited from moving towards an end-to-end learning paradigm: proposals, features, and the classifier becoming one neural network improved results two-fold on general object detection. One indispensable component is non-maximum suppression (NMS), a post-processing algorithm responsible for merging all detections that belong to the same object. The de facto standard NMS algorithm is still fully hand-crafted, suspiciously simple, and -- being based on greedy clustering with a fixed distance threshold -- forces a trade-off between recall and precision. We propose a new network architecture designed to perform NMS, using only boxes and their score. We report experiments for person detection on PETS and for general object categories on the COCO dataset. Our approach shows promise providing improved localization and occlusion handling.