AI Paper Atlas

Research map / Detection and segmentation / CNN features

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

Andrew Shepley, Greg Falzon, Paul Kwan, Ljiljana Branković

TPAMI 2023 · Detection and segmentation › CNN features · approach: Box regression and loss design · 55 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace Greedy NMS and Soft-NMS with ConfluenceRetinaNet · MS-COCO mini-valAP@0.5:0.95: gains in AP of 1.0-1.9%Improved
replace Greedy NMS and Soft-NMS linear with Confluence-NMS (C-NMS)RetinaNet · MS-COCO mini-valAP@0.5:0.95: 1.4-2.3%Improved
replace Greedy NMS and Soft-NMS linear with Confluence-NMSRetinaNet · MS-COCO mini-valAP at IoU 0.5: 1.6-2.7%Improved
replace Greedy NMS and Soft-NMS with ConfluenceRetinaNet · MS-COCO mini-valAR@100: gains of 1.5-5.3%Improved
use Confluence on classes often occluded or dense (person, truck, zebra, banana)RetinaNet · MS-COCO mini-val per classAP: 2.51-9.67%Improved
use Confluence on lone unoccluded classes (laptop, dog, cat, airplane)RetinaNet · MS-COCO mini-val per classAPNo clear effect
replace Greedy NMS and Soft-NMS with ConfluenceMask-RCNN · CrowdHuman validationAP@0.5:0.95: gains in AP of 1.2-4%Improved
replace Greedy NMS and Soft-NMS with ConfluenceMask-RCNN · CrowdHuman validationAR@100: 2.4-7.3%Improved
use Confluence-NMS gaussian instead of Soft-NMS gaussianMask-RCNN · CrowdHuman validationAP@0.5:0.95: 2.9%Improved
use Confluence-NMS gaussian instead of Soft-NMS gaussianRetinaNet · MS-COCO mini-valAP@0.5:0.95: 0.4%Improved
use Confluence threshold Ct instead of IoU threshold in the optimal range (ablation)RetinaNet · MS-COCO mini-valAP variation over threshold: variation in AP for Ct being 0.3% while variation in AP for IoU is 0.6%Improved
use Confluence even at the optimal IoU threshold of baselines (ablation)RetinaNet · MS-COCO mini-valAP@0.5:0.95: approximately 1.5% betterImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy