AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Towards a Universal Model for Cross-Dataset Crowd Counting

Zhiheng Ma, Xiaopeng Hong, Xing Wei, Yunfeng Qiu, Yihong Gong

ICCV 2021 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 59 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 scale distribution alignment (SDA) to jointly trained BLBL · UCF-QNRF (joint multi-dataset training)MAE: 97.3 -> 79.2Improved
add SDA to jointly trained BLBL · Shanghai A (joint multi-dataset training)MAE: 66.1 -> 53.6Improved
add SDA to jointly trained BLBL · UCF CC 50 (joint multi-dataset training)MAE: 231.1 -> 169.4Improved
add SDA to jointly trained CSRNetCSRNet · UCF-QNRF (joint multi-dataset training)MAE: 158.0 -> 96.3Improved
add SDA to jointly trained M-SFANetM-SFANet · UCF-QNRF (joint multi-dataset training)MAE: 111.8 -> 79.5Improved
add SDA to jointly trained DMDM · UCF-QNRF (joint multi-dataset training)MAE: 102.6 -> 80.7Improved
train jointly on multiple datasets without alignmentBL · UCF-QNRFMAE: 88.7 -> 97.3Hurt
train jointly on multiple datasets without alignmentM-SFANet · UCF CC 50MAE: 162.3 -> 233.6Hurt
add SDA to BL trained on each dataset separately (ablation)BL · UCF-QNRF (single-dataset training)MAE: 88.7 -> 83.3Improved
add multi-dataset training to SDA+BL (ablation)SDA+BL · UCF-QNRFMAE: 83.3 -> 79.2Improved
align with ground-truth scale distributions (upper bound) (ablation)BL · UCF CC 50MAE: 229.3 -> 114.7Improved
align with ground-truth scale distributions (upper bound) (ablation)BL · UCF-QNRFMAE: 88.7 -> 66.2Improved

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