AI Paper Atlas

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

Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning

Yue Duan, Taicai Chen, Lei Qi, Yinghuan Shi

ICCV 2025 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 4 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 USP in place of DSGDiCaRL&Fix · CIFAR10-30average accuracy: 77.33 -> 79.66Improved
add USP in place of DSGDDER&Fix · CIFAR100-125average accuracy: 69.14 -> 71.60Improved
add USP in place of DSGDDER&Fix · ImageNet100-13average accuracy: 35.73 -> 46.09Improved
add USP in place of DSGDDER&Fix · ImageNet100-100average accuracy: 62.27 -> 62.29No clear effect
add USP in place of DSGDiCaRL&Fix · CIFAR10-150last accuracy: 79.69 -> 78.21Hurt
add USPUaD-CIE · CUB few-shotaverage accuracy: 64.33 -> 66.43Improved
add USPUaD-CIE · CUB novel classesaverage accuracy: 44.42 -> 55.41Improved
add USPUaD-CIE · CUB base classesaverage accuracy: 72.03 -> 71.07Hurt
add low-confidence samples via DCP (ablation)USP · CIFAR10-30average accuracy: 68.34 -> 81.43Improved
use CUD instead of logit distillation (ablation)USP · CIFAR100-25average accuracy: 53.91 -> 54.36Improved
use CUD instead of feature distillation (ablation)USP · CIFAR100-25average accuracy: 48.16 -> 54.36Improved
use equal FSR weights for unlabeled data (1.0 vs 0.5) (ablation)USP · CIFAR10-30average accuracy: 79.52 -> 81.63Improved

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