AI Paper Atlas

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

Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost

Mingfei Gao, Zizhao Zhang, Guo Yu, Sercan . Arık, Larry S. Davis, Tomas Pfister

ECCV 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 199 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
use consistency-based selection instead of uniform sampling under SSLMixMatch AL · CIFAR-10 (250 labels, SSL)accuracy: 87.78 -> 90.23Improved
use consistency-based selection instead of k-center under SSLMixMatch AL · CIFAR-10 (250 labels, SSL)accuracy: 88.75 -> 90.23Improved
use consistency-based selection instead of uniform at 4000 labelsMixMatch AL · CIFAR-10 (4000 labels, SSL)accuracy: 93.45 -> 94.57Improved
entropy selection instead of uniform under SSLMixMatch AL · CIFAR-10 (500 labels, SSL)accuracy: 90.50 -> 89.95Hurt
add SSL training to AL (vs supervised baselines)active learning · CIFAR-10 (150 labels)accuracy: 48.33 -> 87.57Improved
vary AL batch size 25, 50, 100 (ablation)consistency-based SSL AL · CIFAR-10 (200 labels)accuracy: 89.5, 89.2, 89.3No clear effect
consistency selection in supervised setting vs uniformconsistency sampling · CIFAR-10 supervised (3000 labels)accuracy: 80.81 -> 82.75No clear effect
start with K0=50 instead of 100 labeled samples (ablation)consistency-based SSL AL · CIFAR-10accuracy at 150 labelsHurt
start with K0=100 instead of 150 or 200 (ablation)consistency-based SSL AL · CIFAR-10accuracy under fixed budgetImproved
add SSL training and consistency selection vs best AL baseline VAAL at 40% labelsconsistency-based SSL AL · CIFAR-100accuracy: +22.62% accuracyImproved
same comparison on ImageNet at 40% labelsconsistency-based SSL AL · ImageNetaccuracy: +12.28% accuracyImproved

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