AI Paper Atlas

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

Robust Semi-Supervised Learning by Wisely Leveraging Open-Set Data

Yang Yang, N. Jiang, Yi Xu, De‐Chuan Zhan

TPAMI 2024 · Label-efficient and robust learning › Semi-supervised learning · approach: Safe and realistic semi-supervised learning · 23 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 WiseOpen-L (Otsu)MTC · CIFAR-10 (100 labels)ID accuracy: 80.51 -> 85.69Improved
add WiseOpen-E/L variants (mean over variants)MTC · CIFAR-10 (50 labels)ID accuracy: +2.98Improved
add WiseOpen-E/L variants (mean)OpenMatch · Tiny-ImageNet (50 labels)ID accuracy: +1.94Improved
add WiseOpen-E (mean over thresholds)FixMatch · Tiny-ImageNet (50 labels)ID accuracy: -0.17No clear effect
add WiseOpen-E (mean)FixMatch · CIFAR-100 (100 labels)ID accuracy: -0.04No clear effect
add WiseOpen-E (mean)FreeMatch · CIFAR-10 (400 labels)ID accuracy: +0.60Improved
add WiseOpen-E/L (mean)IOMatch · CIFAR-10 (400 labels)ID accuracy: +0.00No clear effect
add WiseOpen (full gradient-variance selection every epoch)OpenMatch · CIFAR-100 (100 labels)training time: 10h 59m -> 43h 01mHurt
use WiseOpen-L instead of full WiseOpen (ablation)OpenMatch · CIFAR-100 (100 labels)training time: 43h 01m -> 11h 36mImproved
add WiseOpen (mean over variants) at mismatch ratio 0.4OpenMatch · CIFAR-100 (50 labels)ID accuracy: 70.53 -> 71.88Improved
add WiseOpen at mismatch ratio 0.7OpenMatch · CIFAR-100 (50 labels)ID accuracy: -0.14No clear effect
use whole unsupervised loss in gradient-variance selection instead of only L_id or L_ood (ablation)WiseOpen-E · CIFAR-100 (50 labels)ID accuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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