AI Paper Atlas

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

Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning

Jia-Hao Xiao, Ming-Kun Xie, Heng-Bo Fan, Gang Niu, Masashi Sugiyama, Sheng-Jun Huang

ECCV 2024 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 3 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 CAP class-proportion thresholding with metric-adaptive thresholding (MAT) (ablation)CAP baseline · COCO (p=0.05)mAP: 62.43 -> 65.03Improved
add correlative/discriminative feature decoupling (dual-head classifier with patches) (ablation)CAP + MAT · COCO (p=0.05)mAP: 65.03 -> 66.07Improved
add generation/utilization of pseudo-labels decoupling (separate classifier heads) (ablation)CAP + MAT + CDD · COCO (p=0.05)mAP: 66.07 -> 69.30Improved
add GUD decoupling (ablation)CAP + MAT + CDD · VOC (p=0.05)mAP: 77.11 -> 79.26Improved
add MAT to CAP (ablation)CAP · NUS (p=0.20)mAP: 51.06 -> 51.20Improved
use F-beta as MAT metric instead of precision or recallMAT · COCOmAPImproved
vary beta in F-beta metricMAT · COCOmAPNo clear effect
increase number of image patches from 2x2 to 3x3 or 4x4D2L · VOC, COCO, NUS (p=0.05)mAPHurt
vary temperature alpha in spatial weightingD2L · COCO, NUSmAPNo clear effect
use too large or too small temperature alphaD2L · VOCmAPHurt
use D2L+MAT instead of CAP at very low label ratioSSMLL · NUS (p=0.01)mAP: 24.75 -> 38.09Improved
use D2L+MAT instead of CAP on F1 metricsSSMLL · VOC (CF1/OF1)CF1: 69.86 -> 68.50 (p=0.05)Mixed

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