AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization

Qi Wang, Junyu Gao, Wei Lin, Xuelong Li

TPAMI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 541 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
train with denser positive samples alongside negatives (S0+S1 to S0+S3+S4) (ablation)C3F-VGG · NWPU-Crowd (val), S0 MAEMAE: 18.54 -> 147.53Hurt
train each density class separately instead of together (ablation)C3F-VGG · NWPU-Crowd (val), S1MAE: 33.12 -> 21.00Improved
train each density class separately instead of together (ablation)C3F-VGG · NWPU-Crowd (val), S3+S4 (S4 column)MAE: 3997.57 -> 3488.25Improved
add negative samples (S0) to S1 training (ablation)C3F-VGG · NWPU-Crowd (val), S1MAE: 21.00 -> 16.44Improved
add negative samples (S0) to S2 training (ablation)C3F-VGG · NWPU-Crowd (val), S2MAE: 51.01 -> 49.97Improved
add negative samples (S0) to S3+S4 training (ablation)C3F-VGG · NWPU-Crowd (val), S4MAE: 3488.25 -> 2882.23Improved
add negative samples (S0) to S1+...+S4 training (ablation)C3F-VGG · NWPU-Crowd (val), S4MAE: 3997.57 -> 3730.56Improved
use 100% instead of 10% of training data (ablation)C3F-VGG · NWPU-Crowd (val)MAE: 158.35 -> 105.79Improved
evaluate on test set instead of val setSCAR · NWPU-CrowdMAE: 81.57 -> 110.0Hurt
use a stricter localization threshold (sigma_s instead of sigma_l)RAZ_Loc · NWPU-Crowd (val) localizationF1-measure: 62.5 -> 54.5Hurt
use box-supervised detector (Faster RCNN) instead of point-supervised RAZ_Loclocalization · NWPU-Crowd (test)F1-measure: 59.8 -> 6.7Hurt

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