AI Paper Atlas

Research map / Image generation / Image restoration

Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting

Chenfeng Xu, Kai Qiu, Jianlong Fu, Song Bai, Yongchao Xu, Xiang Bai

ICCV 2019 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 159 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 the learning to scale module (L2SM) to SPNSPN · ShanghaiTech Part AMAE: 70.0 -> 64.2Improved
add L2SM to SPNSPN · ShanghaiTech Part BMAE: 9.1 -> 7.2Improved
add L2SM to SPNSPN · UCF_CC_50MAE: 204.7 -> 188.4Improved
add L2SM to SPNSPN · UCF-QNRFMAE: 110.3 -> 104.7Improved
add scale preserving pyramid features (SPN) to VGG16VGG16 baseline · UCF-QNRFMAE: 120.6 -> 110.3Improved
add L2SM to SPN, cross-dataset Part A to UCF_CC_50SPN · Part A -> UCF_CC_50MAE: 368.3 -> 332.4Improved
add L2SM to SPN, cross-dataset UCF-QNRF to Part ASPN · UCF-QNRF -> Part AMAE: 87.9 -> 73.4Improved
increase number of centers from 1 to 3 (G=5) (ablation)SPN+L2SM · ShanghaiTech Part AMAE: 67.2 -> 64.2Improved
increase number of centers from 3 to 5, centralizing every region (G=5) (ablation)SPN+L2SM · ShanghaiTech Part AMAE: 64.2 -> 69.8Hurt
use multipolar center loss instead of scaling directly to average density (S2AD), C=3 (ablation)SPN+L2SM · ShanghaiTech Part AMAE: 67.0 -> 64.2Improved
use G=5 groups instead of G=3 (C=2) (ablation)SPN+L2SM · ShanghaiTech Part AMAE: 65.1 -> 65.4No clear effect
vary K x K division from 2 x 2 to 8 x 8 (one center) (ablation)SPN+L2SM · ShanghaiTech Part AMAE: 68.0 / 67.2 / 67.9 / 68.5No clear effect

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