AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting

Binghui Chen, Zhaoyi Yan, Ke Li, Pengyu Li, Biao Wang, Wangmeng Zuo, Lei Zhang

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain text and graph transfer · 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
merge all datasets for joint training (JT) instead of individual trainingHRNet baseline · SHB (3-Joint)MAE: 8.8 -> 9.3Hurt
merge four datasets for joint training (JT)HRNet baseline · SHB (4-Joint)MAE: 8.8 -> 9.7Hurt
add SE attention to joint trainingHRNet baseline · SHB (3-Joint)MAE: 8.8 -> 9.4Hurt
add VA (variational attention with Gaussian mixture latent) (ablation)JT baseline · SHA/SHB/QNRF (3-Joint)MAE: 60.2 -> 57.5; 9.3 -> 7.6; 92.8 -> 87.9Improved
add clustering labels (InVA c=3) on top of VA (ablation)VA · SHA/SHB/QNRF (3-Joint)MAE: 57.5 -> 57.3; 7.6 -> 7.5; 87.9 -> 86.7Improved
add sub-Gaussian components (k=3) on top of InVA c=3 (ablation)InVA · SHA/SHB/QNRF (3-Joint)MAE: 57.3 -> 56.7; 7.5 -> 6.9; 86.7 -> 85.2Improved
add distribution regularizer L_reg (ablation)DKPNet 4-Joint · NWPU val (4-Joint)MAE: 64.2 -> 61.8Improved
add distribution regularizer L_reg (ablation)DKPNet 4-Joint · QNRF (4-Joint)MAE: 86.9 -> 81.4Improved
replace SE attention with DKPNet domain-specific attention (ablation)SE model · NWPU val (4-Joint)MAE: 66.4 -> 61.8Improved
increase number of clusters c from 3 to 4 (ablation)InVA 3-Joint · SHA (3-Joint)MAE: 57.3 -> 59.6Hurt
increase number of clusters c from 3 to 2 (ablation)InVA 3-Joint · SHB (3-Joint)MAE: 7.5 -> 7.9Hurt
increase sub-Gaussians k from 3 to 4 (ablation)InVA c=3 · SHA (3-Joint)MAE: 56.7 -> 57.7Hurt

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