AI Paper Atlas

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

Self-paced Multi-view Co-training

Fan Ma, Deyu Meng, Xuanyi Dong, Yi Yang

JMLR 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 45 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 self-paced soft co-regularization instead of hardSPamCo · Reuters multilingualaccuracy: 73.28 -> 73.83Improved
use SPamCo(soft) instead of Co-Labelmulti-view SSL · Reuters multilingualaccuracy: 72.45 -> 73.83Improved
draw unlabeled data with replacement in co-training (ablation)Cotrain · Market-1501 two-view (R50+D121)MAP: 67.0 -> 67.7Improved
use SPamCo(soft) instead of Cotrain(Rep) selecting pseudo-labels from all viewsco-training with replacement · Market-1501 two-view (R50+D121)MAP: 67.7 -> 69.5Improved
add update of pseudo-labels of unlabeled examples (vs fixed labels) with hard term (ablation)SPamCo(hard) · Market-1501 triple-viewMAP: 64.8 -> 71.3Improved
add update of pseudo-labels with soft term (ablation)SPamCo(soft) · Market-1501 triple-viewMAP: 67.3 -> 71.8Improved
add update of pseudo-labels with hard term (ablation)SPamCo(hard) · Market-1501 triple-viewrank-1 accuracy: 83.1 -> 87.0Improved
use parallel instead of serial training of view classifiers (ablation)SPamCo(soft) · Market-1501 triple-viewMAP: 71.8 -> 71.7No clear effect
use three views instead of two viewsSPamCo(soft) · Market-1501MAP: 69.5 -> 71.8Improved
increase number of added unlabeled instances per iteration (ablation)SPamCo · Reuters multilingualaccuracyMixed
use soft instead of hard regularization when labels are fixed (ablation)SPamCo · Market-1501 triple-viewMAP: 54.7 -> 57.3Improved
use SPamCo(Psoft) instead of ICT with 4000 labelssemi-supervised CIFAR-10 · CIFAR-10 (4000 labels)error rate (%): 7.66 -> 7.05Improved

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