AI Paper Atlas

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

On the Calibration of Image Semi-Supervised Learning Models

Mehrab Mustafy Rahman, Jayanth Mohan, Tiberiu Sosea, Cornelia Caragea

AAAI 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 0 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 CalibrateMix targeted mixup to FixMatchFixMatch · CIFAR-100 (25 labels/class)ECE (%): 21.19 -> 12.68Improved
add CalibrateMix to SoftMatchSoftMatch · CIFAR-100 (25 labels/class)top-1 error (%): 26.76 -> 26.86No clear effect
add CalibrateMix to FlexMatchFlexMatch · CIFAR-100 (25 labels/class)ECE (%): 29.54 -> 28.23Mixed
add CalibrateMix to SoftMatchSoftMatch · STL-10 (4 labels/class)top-1 error (%): 20.90 -> 15.18Improved
add CalibrateMix to FixMatch at 4 labels/classFixMatch · CIFAR-10 (4 labels/class)ECE (%): 5.42 -> 3.24Improved
add CalibrateMix to fully supervised trainingFullySupervised · CIFAR-100ECE (%): 6.77 -> 4.74Improved
use targeted CalibrateMix mixup instead of random mixup (ablation)FixMatch · CIFAR-100 (4 labels/class)ECE (%): 38.05 -> 35.43Improved
add CalibrateMix on top of label smoothing (ablation)FixMatch + LS · CIFAR-100 (25 labels/class)ECE (%): 17.37 -> 12.89Improved
add CalibrateMix on top of label smoothing (ablation)SoftMatch + LS · CIFAR-10/CIFAR-100/STL-10 (error rate)top-1 error (%): CIFAR-100 25 labels: 26.50 -> 27.41Mixed
restrict mixup to easy/hard labeled-unlabeled pairs instead of mixing all pairs (ablation)SoftMatch + CalibrateMix · CIFAR-100 (4 labels/class)ECE (%): 30.63 -> 23.1Improved
add warmup (ablation)mixup-all SoftMatch · CIFAR-100 (4 labels/class)top-1 error (%): 86.95 -> 41.5Improved
add cosine-dissimilarity sample selection (k=5%) (ablation)SoftMatch + CalibrateMix · STL-10 (4 labels/class)ECE (%): 16.81 -> 12.4Improved

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