Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection

2020-12-01 · Andrew Shepley, Greg Falzon, Paul Kwan

Confluence is a novel non-Intersection over Union (IoU) alternative to Non-Maxima Suppression (NMS) in bounding box post-processing in object detection. It overcomes the inherent limitations of IoU-based NMS variants to provide a more stable, consistent predictor of bounding box clustering by using a normalized Manhattan Distance inspired proximity metric to represent bounding box clustering. Unlike Greedy and Soft NMS, it does not rely solely on classification confidence scores to select optimal bounding boxes, instead selecting the box which is closest to every other box within a given cluster and removing highly confluent neighboring boxes. Confluence is experimentally validated on the MS COCO and CrowdHuman benchmarks, improving Average Precision by up to 2.3-3.8% and Average Recall by up to 5.3-7.2% when compared against de-facto standard and state of the art NMS variants. Quantitative results are supported by extensive qualitative analysis and threshold sensitivity analysis experiments support the conclusion that Confluence is more robust than NMS variants. Confluence represents a paradigm shift in bounding box processing, with potential to replace IoU in bounding box regression processes.

📄 PDF Abstract BibTeX arXiv:2012.00257

Code (3)

ashep29/confluence 공식 구현

Huangdebo/Confluence pytorch

lmk123568/OD_Confluence

Tasks

Clusteringobject-detection Object Detection

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Residual Connection 설명 없음

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Batch Normalization 설명 없음

k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…

BNB Customer Service Number +1-833-534-1729 설명 없음

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Improved Person Detection on Omnidirectional Images with Non-maxima Suppression

2018-05-22 · Roman Seidel, André Apitzsch, Gangolf Hirtz

We propose a person detector on omnidirectional images, an accurate method to generate minimal enclosing rectangles of persons. The basic idea is to adapt the qualitative detection performance of a convolutional neural n…

Human Detection

Faster than FAST: GPU-Accelerated Frontend for High-Speed VIO

2020-03-30 · Balazs Nagy, Philipp Foehn, Davide Scaramuzza

The recent introduction of powerful embedded graphics processing units (GPUs) has allowed for unforeseen improvements in real-time computer vision applications. It has enabled algorithms to run onboard, well above the st…

CPU feature selection GPU State Estimation+1

Learned Non-Maximum Suppression for 3D Object Detection

2026-06-02 · Timo Osterburg, Stefan Schütte, Torsten Bertram arxiv

Post-processing is a critical stage in LiDAR-based 3D object detection, where dense and overlapping proposals must be filtered for compact and reliable perception. This work introduces two learned filtering modules that …

3D Object Detection

End-to-End Integration of a Convolutional Network, Deformable Parts Model and Non-Maximum Suppression

2014-11-19 · Li Wan, David Eigen, Rob Fergus

Deformable Parts Models and Convolutional Networks each have achieved notable performance in object detection. Yet these two approaches find their strengths in complementary areas: DPMs are well-versed in object composit…

Object object-detection Object Detection

End-to-End Integration of a Convolution Network, Deformable Parts Model and Non-Maximum Suppression

2015-06-01 · CVPR 2015 6 · Li Wan, David Eigen, Rob Fergus