AI Paper Atlas

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

A Machine Teaching Framework for Scalable Recognition

Pei Wang, Nuno Vasconcelos

ICCV 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Self-training theory · 5 citations (OpenAlex)

Read the paper

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 counterfactual explanations (CMaxGrad instead of MaxGrad)MaxGrad teaching · Butterflies (MTurker labeling)labeling accuracy: 80.33 -> 84.10Improved
add counterfactual explanations (CMaxGrad instead of MaxGrad)MaxGrad teaching · Chinese Characters (MTurker labeling)labeling accuracy: 81.89 -> 84.63Improved
add counterfactual explanations to MaxGradMEMORABLE · Butterflies (scalable recognition)test accuracy: 74.7 -> 77.5Improved
add counterfactual explanations to MaxGradMEMORABLE · Gull (scalable recognition)test accuracy: 56.3 -> 60.2 (about 4%)Improved
add DivideMix noisy-label training to CMaxGradMEMORABLE · Butterflies (scalable recognition)test accuracy: 77.5 -> 81.2Improved
add DivideMix noisy-label training to CMaxGradMEMORABLE · Gull (scalable recognition)test accuracy: 60.2 -> 61.7Improved
add DivideMix noisy-label training to MaxGradMEMORABLE · Butterflies (scalable recognition)test accuracy: 74.7 -> 78.6Improved
add DivideMix noisy-label training to MaxGradMEMORABLE · Gull (scalable recognition)test accuracy: 56.3 -> 59.9Improved
use SimCLR semi-supervised model to generate counterfactual explanations (ablation)CMaxGrad · Butterflies and Gulltest accuracy: Butterflies 77.5 -> 78.2; Gull 60.2 -> 59.7Mixed
add SimCLR-based explanations to CMaxGrad+DivideMix (ablation)MEMORABLE · Butterflies (scalable recognition)test accuracy: 81.2 -> 83.4Improved
add SimCLR-based explanations to CMaxGrad+DivideMix (ablation)MEMORABLE · Gull (scalable recognition)test accuracy: 61.7 -> 61.2Hurt
use SimCLR alone (self-supervised) instead of supervised baselineSimCLR · Gull (scalable recognition)test accuracy: 58.3 -> 53.0Hurt

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