AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks

Yan Liu, Lingqiao Liu, Peng Wang, Pingping Zhang, Yinjie Lei

ECCV 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Pseudo-labeling for specialized tasks · 93 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 unlabeled images for surrogate-task feature learning (vs labeled only) (ablation)IRAST · ShanghaiTech Part AMAE: 94.1 -> 86.9Improved
add unlabeled images for surrogate-task feature learning (vs labeled only) (ablation)IRAST · UCF-QNRFMAE: 140.8 -> 135.6Improved
add inter-relationship constraint to pseudo-label generation (ablation)IRAST · ShanghaiTech Part AMAE: 93.5 -> 86.9Improved
add inter-relationship constraint to pseudo-label generation (ablation)IRAST · UCF-QNRFMAE: 139.8 -> 135.6Improved
use 3 binary surrogate tasks rather than one multi-class segmentation (MSST) (ablation)IRAST · ShanghaiTech Part AMAE: 91.5 -> 86.9Improved
use 3 binary surrogate tasks rather than one multi-class segmentation (MSST) (ablation)IRAST · UCF-QNRFMAE: 140.0 -> 135.6Improved
raise confidence threshold t_p from 0.6 to 0.9 (ablation)IRAST · ShanghaiTech Part AMAE: 88.4 -> 86.9No clear effect
raise confidence threshold t_p from 0.6 to 0.9 (ablation)IRAST · UCF-QNRFMAE: 137.2 -> 135.6No clear effect
add IRAST on top of CSRNet feature extractorCSRNet · ShanghaiTech Part AMAE: 98.3 -> 86.9Improved
add IRAST on top of SPN feature extractor (ablation)SPN · ShanghaiTech Part AMAE: 88.5 -> 83.9Improved
add IRAST on top of SPN feature extractor (ablation)SPN · UCF-QNRFMAE: 138.0 -> 128.4Improved
use 3 surrogate tasks instead of 1 (ablation)IRAST · ShanghaiTech Part AMAE: 89.8 -> 86.9Improved

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