AI Paper Atlas

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

Stochastic Consensus: Enhancing Semi-Supervised Learning with Consistency of Stochastic Classifiers

Hui Tang, Lin Sun, Kui Jia

ECCV 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 5 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 consistency criterion among stochastic classifiers (ablation)STOCO · CIFAR-10 (40 labels)error rate: 9.25 -> 4.74Improved
add deep discriminative clustering pseudo labels (ablation)STOCO w/o CC · CIFAR-10 (40 labels)error rate: 11.27 -> 9.25Improved
use stochastic classifier instead of deterministic one (m=1 vs w/o CC) (ablation)STOCO · CIFAR-10 (40 labels)error rate: 9.25 -> 8.46Improved
increase number of stochastic classifiers from 1 to 5 (ablation)STOCO · CIFAR-10 (40 labels)error rate: 8.46 -> 4.74Improved
increase number of stochastic classifiers from 5 to 20 (ablation)STOCO · CIFAR-10 (40 labels)error rate: 4.74 -> 7.19Hurt
add stochastic consensus to FixMatchFixMatch · CIFAR-100 (400 labels)error rate: 48.85 -> 41.45Improved
add stochastic consensus to FixMatchFixMatch · CIFAR-10 (40 labels)error rate: 13.81 -> 7.17Improved
add stochastic consensus to FixMatchFixMatch · CIFAR-10 (4000 labels)error rate: 4.26 -> 3.86Improved
add stochastic consensus to FixMatchFixMatch · SVHN (1000 labels)error rate: 2.28 -> 2.38No clear effect
add stochastic consensus to FixMatchFixMatch · STL-10 (1000 labels)error rate: 7.98 -> 7.79Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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