AI Paper Atlas

Research map / Detection and segmentation / CNN features

Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds

Haroon Idrees, Muhmmad Tayyab, Kishan Athrey, Dong Zhang, Somaya Al-Maadeed, Nasir Rajpoot, Mubarak Shah

ECCV 2018 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 904 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
connect Density Network to DenseBlock2 rather than DenseBlock4 (ablation)Composition Loss network · UCF-QNRF countC-MAE: 148 -> 132Improved
connect Density Network to DenseBlock2 rather than DenseBlock3 (ablation)Composition Loss network · UCF-QNRF countC-MAE: 144 -> 132Improved
use all three maps (add D_inf localization map) instead of D1 and D2 only (ablation)Composition Loss network · UCF-QNRF countC-MAE: 137 -> 132Improved
use D1 and D2 rather than D1 only (ablation)Composition Loss network · UCF-QNRF countC-MAE: 141 -> 137Improved
add multiple density levels with Composition Loss to the base DenseNet201 counter (ablation)DenseNet201 · UCF-QNRF countC-MAE: 163 -> 132Improved
keep density maps unconnected to the count output instead of concatenating map counts (ablation)Composition Loss network · UCF-QNRF countC-MAE: 139 -> 132Improved
keep density maps unconnected to the count output instead of taking mean of four counts (ablation)Composition Loss network · UCF-QNRF countC-MAE: 150 -> 132Improved
enforce mean of counts from all sources (Mean) instead of unconnected maps (ablation)Composition Loss network · UCF-QNRF D_1 density mapMAE: 1629 -> 1151Mixed
replace best prior counting method (Densenet201) with proposedDensenet201 · UCF-QNRFC-MAE: 163 -> 132Improved
replace best prior localizer (Encoder-Decoder) with proposedEncoder-Decoder · UCF-QNRF localizationL-AUC: 0.670 -> 0.714Improved

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