AI Paper Atlas

Research map / Detection and segmentation / CNN features

Optimal Proposal Learning for Deployable End-to-End Pedestrian Detection

Xiaolin Song, Binghui Chen, Pengyu Li, Jun-Yan He, Biao Wang, Yifeng Geng, Xuansong Xie, Honggang Zhang

CVPR 2023 · Detection and segmentation › CNN features · approach: Pedestrian and crowd detection · 24 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 FCOS with OPLpedestrian detection · CrowdHuman valmMR: 45.6 -> 44.9Improved
replace FCOS with OPLpedestrian detection · CrowdHuman valAP: 90.7 -> 91.0Improved
replace FCOS with OPLpedestrian detection · TJU-Ped-campusmMR (RS): 62.7 -> 61.7Improved
replace FCOS with OPLpedestrian detection · TJU-Ped-trafficmMR (A): 39.7 -> 38.7Improved
replace FCOS with OPLpedestrian detection · Caltech testmMR (R): 6.9 -> 5.2Improved
add C2F and CPN (ablation)FCOS one-to-one detector · CrowdHuman valmMR: 49.3 -> 44.9Improved
add C2F (ablation)FCOS one-to-one detector · CrowdHuman valmMR: 49.3 -> 47.2Improved
add CPN (ablation)FCOS one-to-one detector · CrowdHuman valmMR: 49.3 -> 47.0Improved
use two C2F refinement steps with M={16,4} (ablation)OPL with CPN · CrowdHuman valmMR: 47.0 -> 44.9Improved
use C2F-1step with M={4} (ablation)OPL with CPN · CrowdHuman valmMR: 47.0 -> 46.1Improved
use C2F-1step with M={9} (ablation)OPL with CPN · CrowdHuman valmMR: 47.0 -> 45.8Improved
use C2F-1step with M={16} (ablation)OPL with CPN · CrowdHuman valmMR: 47.0 -> 46.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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