atlas

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

Almost Unsupervised Learning for Dense Crowd Counting

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 114 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 GWTA sparsity to stacked autoencoder pretraining (ablation)GWTA-CCNN · ShanghaiTech Part AMAE: 193.0 -> 154.7Helped
add GWTA sparsity to stacked autoencoder pretraining (ablation)GWTA-CCNN · UCF_CC_50MAE: 448.3 -> 433.7Helped
use tied decoder instead of untied large-filter decoder (ablation)GWTA-CCNN · ShanghaiTech Part AMAE: 195.6 -> 154.7Helped
use tied decoder instead of untied large-filter decoder (ablation)GWTA-CCNN · UCF_CC_50MAE: 500.3 -> 433.7Helped
GWTA unsupervised pretraining instead of self-supervised colorization/inpaintingCCNN · ShanghaiTech Part AMAE: 166.3 -> 154.7Helped
GWTA unsupervised pretraining instead of full supervisionCCNN · ShanghaiTech Part AMAE: 124.6 -> 154.7Hurt
GWTA pretraining with very few labeled imagesCCNN · ShanghaiTech Part AMAEMixed

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