AI Paper Atlas

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

Semi-Supervised Learning by Augmented Distribution Alignment

Qin Wang, Wen Li, Luc Van Gool

ICCV 2019 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 85 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 adversarial distribution alignment (ablation)baseline CNN · CIFAR10error rate (%): 19.97% -> 18.67%Improved
add adversarial distribution alignment (ablation)baseline CNN · SVHNerror rate (%): 13.80% -> 10.76%Improved
add cross-set sample augmentation (ablation)baseline CNN · CIFAR10error rate (%): 19.97% -> 13.79%Improved
add cross-set sample augmentation (ablation)baseline CNN · SVHNerror rate (%): 13.80% -> 10.74%Improved
add distribution alignment on top of cross-set augmentation (ablation)ADA-Net · CIFAR10error rate (%): 13.79% -> 8.87%Improved
add cross-set augmentation on top of distribution alignment (ablation)ADA-Net · CIFAR10error rate (%): 18.67% -> 8.87%Improved
add distribution alignment on top of cross-set augmentation (ablation)ADA-Net · SVHNerror rate (%): 10.74% -> 5.90%Improved
add cross-set augmentation on top of distribution alignment (ablation)ADA-Net · SVHNerror rate (%): 10.76% -> 5.90%Improved
add ADA-Net modules to VAT+EntVAT+Ent · SVHNerror rate (%): 3.86% -> 3.54%Improved
add ADA-Net modules to VAT+EntVAT+Ent · CIFAR10error rate (%): 10.55% -> 10.09%Improved
use larger translation range (4 instead of 2) and no ZCA whiteningADA-Net · CIFAR10error rate (%): 10.30% -> 8.72%Improved
fewer labeled samples (1000 down to 200)baseline CNN · SVHNerror rate (%)Hurt

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