AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Exploiting Sample Correlation for Crowd Counting With Multi-Expert Network

Xinyan Liu, Guorong Li, Zhenjun Han, Weigang Zhang, Yifan Yang, Qingming Huang, Nicu Sebe

ICCV 2021 · Architectures and efficiency › Pruning and efficient tuning · approach: Parameter-efficient transfer analysis · 36 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 multi-expert strategyFDC-18 · ShanghaiTech Part AMAE: 65.4 -> 55.4Improved
add multi-expert strategyFDC-18 · ShanghaiTech Part BMAE: 11.4 -> 6.9Improved
add multi-expert strategyFDC-18 · UCF-QNRFMAE: 93.0 -> 76.2Improved
add multi-expert strategyFDC-18 · NWPU-Crowd testMAE: 119.39 -> 74.7Improved
add multi-expert strategyCSRNet · UCF-QNRFMAE: 98.2 -> 83.1Improved
add multi-expert strategyMCNN · UCF-QNRFMAE: 277 -> 234.1Improved
add multi-expert strategyMCNN · ShanghaiTech Part AMAE: 110.6 -> 94.1Improved
add multi-expert strategyCSRNet · ShanghaiTech Part AMAE: 68.2 -> 60.1Improved
select unstable samples instead of hard samples for subset Q (ablation)MFDC (NWPU) · NWPU-CrowdMAEImproved
change number of clusters (merge smallest or split biggest) away from the adaptive number (ablation)MFDC · ShanghaiTech Part AMAEHurt
use co-fine-tune clustering instead of IG-CNN style divide-and-grow clusters (ablation)MFDC · ShanghaiTech Part Alabel consistency and router accuracyImproved
use multi-expert model trained on NWPU without target trainingMFDC-18 vs FDC-18 fine-tuned · ST Part A (transfer)MAE: 63.1 -> 56.9Improved

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