AI Paper Atlas

Research map / Detection and segmentation / CNN features

Localization in the Crowd with Topological Constraints

Shahira Abousamra, Minh Hoai, Dimitris Samaras, Chao Chen

AAAI 2021 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 124 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 persistence loss to DICE training (ablation)TopoCount · ShanghaiTech AGAME G(3): 114 -> 104Improved
Replace weighted BCE with DICE plus persistence loss (ablation)TopoCount · ShanghaiTech AGAME G(3): 122 -> 104Improved
Set persistence-loss weight λ to 1.5 rather than 1.0 (ablation)TopoCount · ShanghaiTech AGAME G(3): 104 -> 104No clear effect
Set persistence-loss weight λ to 2.0 rather than 1.0 (ablation)TopoCount · ShanghaiTech AGAME G(3): 104 -> 107Hurt
Use 50×50 instead of 150×150 persistence-loss patches (ablation)TopoCount · ShanghaiTech AGAME G(3): 114.2 -> 104.9Improved
Use 50×50 instead of 30×30 persistence-loss patches (ablation)TopoCount · ShanghaiTech AGAME G(3): 108.2 -> 104.9Improved
Use 100×100 instead of 30×30 persistence-loss patches (ablation)TopoCount · UCF-QNRFGAME G(3): 222.1 -> 206.6Improved
Use 100×100 instead of 150×150 persistence-loss patches (ablation)TopoCount · UCF-QNRFGAME G(3): 208.5 -> 206.6Improved
Concatenate TopoCount maps as extra inputs to CANCAN · ShanghaiTech AMAE: 62.3 -> 59.5Improved
Concatenate TopoCount maps as extra inputs to BayesianBayesian · ShanghaiTech AMAE: 62.8 -> 58Improved
Concatenate TopoCount maps as extra inputs to CANCAN · ShanghaiTech BRMSE: 12.2 -> 13.2Hurt
Concatenate TopoCount maps as extra inputs to BayesianBayesian · JHU++ validationMAE: 59.3 -> 54.1Improved

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