AI Paper Atlas

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

Acknowledging the Unknown for Multi-Label Learning with Single Positive Labels

Donghao Zhou, Pengfei Chen, Qiong Wang, Guangyong Chen, Pheng-Ann Heng

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 41 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
replace assuming-negative loss with entropy-maximization loss on unannotated labelsResNet-50 SPML · CUBmAP: 18.31 -> 20.85Improved
replace assuming-negative loss with entropy-maximization lossResNet-50 SPML · COCOmAP: 64.92 -> 70.70Improved
replace assuming-negative loss with entropy-maximization lossResNet-50 SPML · VOCmAP: 85.89 -> 89.09Improved
add asymmetric pseudo-labeling to EM lossEM loss · CUBmAP: 20.85 -> 21.84Improved
add asymmetric pseudo-labeling to EM lossEM loss · VOCmAP: 89.09 -> 89.19Improved
add entropy minimization regularization instead of entropy maximizationAN loss · VOCmAP: 85.89 -> 53.16Hurt
use high sample proportion (90%) for negative pseudo-labels instead of 10% (ablation)APL · CUBmAP: 20.95 -> 21.84Improved
use soft pseudo-labels instead of hard ones (ablation)APL · CUBmAP: 20.99 -> 21.84Improved
add down-weighting of pseudo-label loss (beta<1) (ablation)APL · CUBmAP: 21.00 -> 21.84Improved
add positive pseudo-labeling at 10% proportion (ablation)APL · CUBmAP: 21.84 -> 20.82Hurt
use ResNet-101 backbone instead of ResNet-50 (ablation)EM loss · VOCmAP: 89.09 -> 88.80Hurt
use EM loss instead of AN loss for APL pseudo-label generation (ablation)APL · VOCpseudo-label precision (%): 96.44 -> 99.57Improved

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