AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Uniformity in Heterogeneity: Diving Deep Into Count Interval Partition for Crowd Counting

Changan Wang, Qingyu Song, Boshen Zhang, Yabiao Wang, Ying Tai, Xuyi Hu, Chengjie Wang, Jilin Li, Jiayi Ma, Yang Wu

ICCV 2021 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection · 50 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 mean count proxies (MCP) (ablation)UEPNet · SHTech Part AMAE: 61.56 -> 58.69Improved
add mean count proxies (MCP) (ablation)UEPNet · SHTech Part BMAE: 7.72 -> 7.64Improved
add interleaved prediction heads (IPH) over MCP (ablation)UEPNet · SHTech Part AMAE: 58.69 -> 56.80Improved
add interleaved prediction heads (IPH) over MCP (ablation)UEPNet · SHTech Part BMAE: 7.64 -> 7.25Improved
use parallel heads with identical intervals (PPH) instead of IPH (ablation)UEPNet · SHTech Part AMAE: 58.69 -> 58.47No clear effect
use parallel heads with identical intervals (PPH) instead of IPH (ablation)UEPNet · SHTech Part BMAE: 7.64 -> 7.57No clear effect
add multi-scale training to MCP+IPH (ablation)UEPNet · SHTech Part AMAE: 56.80 -> 54.64Improved
add multi-scale training to MCP+IPH (ablation)UEPNet · SHTech Part BMAE: 7.25 -> 6.38Improved
divide intervals with UEP instead of UniformLen (median proxy) (ablation)UEPNet · SHTech Part BMAE: 82.62 -> 7.72Improved
divide intervals with UEP instead of UniformNum (median proxy) (ablation)UEPNet · SHTech Part BMAE: 62.46 -> 7.72Improved
use MCP instead of median count proxy with UEP intervals (ablation)UEPNet · SHTech Part B discretization errordiscretization error: 1.88 -> 0.27Improved
add multi-scale training to MSE regression (ablation)MSE regression baseline · SHTech Part BMAE: 13.57 -> 14.65Hurt

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