AI Paper Atlas

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

Universal Semi-Supervised Learning

Zhuo Huang, Chao Xue, Bo Han, Jian Yang, Chen Gong

NeurIPS 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Safe and realistic semi-supervised learning · 9 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 CAFA (class-sharing detection + feature adaptation)PI · CIFAR-10 subset mismatchtest accuracy %: 75.02 -> 79.36Improved
add CAFAFixMatch · CIFAR-10 subset mismatchtest accuracy %: 80.19 -> 83.97Improved
add CAFAFixMatch · CIFAR-10 intersectional mismatchtest accuracy %: 80.01 -> 81.28Improved
add CAFAPI · Office-31 A/D feature mismatchtest accuracy %: 49.29 -> 81.97Improved
add CAFAPI · VisDA2017 feature mismatchtest accuracy %: 27.00 -> 91.02Improved
use closed-set/open-set SSL methods under feature mismatch instead of supervised onlyMean Teacher / FixMatch · Office-31 D/A feature mismatchtest accuracy %: 58.23 -> 55.65 (MT), 61.05 (FM)Mixed
add CAFAPI · Office-31 A/W subset+feature mismatchtest accuracy %: 56.97 -> 82.49Improved

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