AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting

Xiyang Liu, Jie Yang, Wenrui Ding, Tieqiang Wang, Zhijin Wang, Junjun Xiong

ECCV 2020 · Architectures and efficiency › CNN design · approach: Higher-order pooling · 149 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
regress local counting map instead of density map (ablation)VGG16 · ShanghaiTech Part AMAE: 72.98 -> 69.52Improved
regress local counting map instead of density map (ablation)VGG16 · ShanghaiTech Part BMAE: 9.79 -> 8.96Improved
regress local counting map instead of density map (ablation)VGG16 · ShanghaiTech Part AMSE: 114.89 -> 110.23Improved
add mixture regression module (MRM) to LCM baseline (ablation)VGG16+LCM · ShanghaiTech Part AMAE: 69.52 -> 65.24Improved
add mixture regression module (MRM) to LCM baseline (ablation)VGG16+LCM · ShanghaiTech Part BMAE: 8.96 -> 7.79Improved
add adaptive soft interval module (ASIM) (ablation)MRM · ShanghaiTech Part AMAE: 65.24 -> 63.85Improved
add adaptive soft interval module (ASIM) (ablation)MRM · ShanghaiTech Part BMAE: 7.79 -> 7.56Improved
add scale-aware module (SAM) (ablation)MRM+ASIM · ShanghaiTech Part AMAE: 63.85 -> 61.59Improved
add scale-aware module (SAM) (ablation)MRM+ASIM · ShanghaiTech Part BMAE: 7.56 -> 7.02Improved
use 64x64 local patch instead of 16x16 (ablation)MRM · ShanghaiTech Part AMAE: 70.45 -> 65.24Improved
use 64x64 local patch instead of 128x128 (ablation)MRM · ShanghaiTech Part AMAE: 67.73 -> 65.24Improved
use 64x64 local patch instead of 128x128 (ablation)MRM · ShanghaiTech Part BMAE: 7.93 -> 7.79Improved

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