AI Paper Atlas

Research map / Detection and segmentation / CNN features

Progressive Refinement Network for Occluded Pedestrian Detection

Xiaolin Song Kaili Zhao Wen-Sheng Chu Honggang Zhang Jun Guo

ECCV 2020 · Detection and segmentation › CNN features · approach: Pedestrian and crowd detection · 60 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
add visible-part estimation and anchor calibration before the full-body refiner (ablation)PRNet-F · CityPersons valMR-2 R: 15.6 -> 11.4Improved
add visible-part estimation and anchor calibration before the full-body refiner (ablation)PRNet-F · CityPersons valMR-2 HO: 45.7 -> 45.3Improved
use VE+AC alone instead of a standalone full-body detector (ablation)PRNet-F · CityPersons valMR-2 R / HO: R 15.6 -> 11.7, HO 45.7 -> 51.3Mixed
add full-body refinement after VE+AC (ablation)PRNet-VA · CityPersons valMR-2 HO: 51.3 -> 45.3Improved
add full-body refinement after VE+AC (ablation)PRNet-VA · CityPersons valMR-2 R: 11.7 -> 11.4Improved
use anchor calibration instead of a learned box regressor from visible to full-body boxes (ablation)PRNet-VAF · CityPersons valMR-2 R: 12.6 -> 11.4Improved
use anchor calibration instead of a learned box regressor (ablation)PRNet-VAF · CityPersons valMR-2 HO: 44.7 -> 45.3Hurt
add occlusion loss (ablation)PRNet-VAF · CityPersons valMR-2 R / HO: R 11.4 -> 11.0, HO 45.3 -> 45.7Mixed
add Receptive Field Backfeed (RFB) (ablation)PRNet-VAF · CityPersons valMR-2 R / HO: R 11.4 -> 11.6, HO 45.3 -> 44.9Mixed
add both occlusion loss and RFB (ablation)PRNet-VAF · CityPersons valMR-2 R / HO: R 11.4 -> 10.8, HO 45.3 -> 42.0Improved
PRNet versus ALFNet on the Heavy subsetPRNet · CityPersons valMR-2 Heavy: 51.9 -> 53.3Hurt
PRNet versus ALFNet cross-dataset to ETHPRNet · ETH (trained on CityPersons)MR-2 R+HO: 31.1 -> 27.0Improved

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