AI Paper Atlas

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

IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization

Zekun Li, Lei Qi, Yinghuan Shi, Yang Gao

ICCV 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 38 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
use joint inlier and outlier utilization via open-set classifier loss L_opIOMatch · CIFAR (ablation A1-A3)closed-set accuracyImproved
add multi-binary classifier alone to FixMatch-like baselineIOMatch · CIFAR (ablation A2 vs A1)closed-set accuracyImproved
keep unsupervised training loss L_ui of closed-set classifierIOMatch · CIFAR (ablation A3)closed-set accuracyImproved
decouple feature spaces by using a projection head for multi-binary and open-set classifiers (ablation)IOMatch · CIFAR-50-200accuracy: about 2.2% drop when sharedImproved
add rotation recognition auxiliary objectiveIOMatch · CIFAR-100 50/50, 4 labelsaccuracy: 56.14 -> 58.92Improved
add SimMatch contrastive objectiveIOMatch · CIFAR-100 50/50, 4 labelsaccuracy: 56.14 -> 57.08Improved
lower the open-set confidence threshold tau_q (at most 0.75)IOMatch · CIFARaccuracyImproved
vary loss weights away from 1 (too small or too large)IOMatch · CIFARaccuracyHurt
set tau_p to 0 versus 0.95IOMatch · CIFARaccuracyMixed
present outliers in unlabeled data versus standard SSL with no outliersIOMatch · CIFAR-50-200accuracy: 55.94 -> 56.14Improved
IOMatch versus strongest rivals when labels are scarce and class mismatch severeIOMatch · CIFAR-6-24, CIFAR-20-80, CIFAR-50-200accuracy: +3.60%, +7.46%, +4.78%Improved
IOMatch versus SimMatch when more labels are availableIOMatch · CIFAR-100 80/20, 25 labelsaccuracy: 65.68 -> 64.75Hurt

Later papers that compared with this method

7 later accepted papers report IOMatch as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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