AI Paper Atlas

Research map / Benchmarks / CIFAR-10 (250 labels)

CIFAR-10 (250 labels) leaderboard

29 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CIFAR-10 (250 labels). Best error rate: 4.21 (RegMixMatch, AAAI 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CIFAR-10 (250 labels) · error rate

18 papers, each with its best reported number for its own method; lower is better.

#error rate ↓MethodPaperTopic
14.21RegMixMatch
Wide ResNet-28-2
RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning
AAAI 2025 · Table 1
Semi-supervised learning
24.22FlatMatch
WRN-28-2
FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning
NeurIPS 2023 · Table 1
Semi-supervised learning
34.53GSF
WRN-28-2
Towards Discovering the Effectiveness of Moderately Confident Samples for Semi-Supervised Learning
CVPR 2022 · Table 1
Semi-supervised learning
44.56FreeMatch + Maximizing Mutual Information
FreeMatch
Unveiling the Dynamics of Information Interplay in Supervised Learning
ICML 2024 · Table: Error rates on CIFAR-10
Semi-supervised learning
54.6OTMatch
Wide ResNet28-2
OTMatch: Improving Semi-Supervised Learning with Optimal Transport
ICML 2024 · Table 1
Semi-supervised learning
64.7ConMatch-PConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization
ECCV 2022 · Table 1
Semi-supervised learning
74.71BidMatch
WRN
BidMatch: Boosting Semi-Supervised Learning by Bi-Dimensional Sample Weight Guidance
AAAI 2026 · Table 2
Semi-supervised learning
84.77STOCO
WRN-28-2
Stochastic Consensus: Enhancing Semi-Supervised Learning with Consistency of Stochastic Classifiers
ECCV 2022 · Table 2
Semi-supervised learning
94.78DP-SSL
WRN-28-2 (WRN-28-8 for CIFAR-100)
DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples
NeurIPS 2021 · Table 1
Semi-supervised learning
104.8USADTM
Wide ResNet-28-2
Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning
NeurIPS 2020 · Table 1
Semi-supervised learning
8 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

CIFAR-10 (250 labels) · accuracy

11 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
198.08InstanT
pre-trained ViT
InstanT: Semi-supervised Learning with Instance-dependent Thresholds
NeurIPS 2023 · Table 1
Semi-supervised learning
295.76PMLP+LASSL
LASSL
Probability-Density-aware Semi-supervised Learning
AAAI 2025 · Table 1
Semi-supervised learning
395.4FlexMatch (w/SAA)
FlexMatch, WRN-28-2
Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning
ICCV 2023 · Table 1
Semi-supervised learning
495.36FullMatch
FixMatch
Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data
CVPR 2023 · Table 1
Semi-supervised learning
595.1FixMatch (STS)
FixMatch
Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework
NeurIPS 2021 · Table 6
Knowledge distillation
695.09CoMatch
WRN-28-2
CoMatch: Semi-Supervised Learning With Contrastive Graph Regularization
ICCV 2021 · Table 1
Semi-supervised learning
795.03AlphaMatch
WRN-28-2
AlphaMatch: Improving Consistency for Semi-Supervised Learning With Alpha-Divergence
CVPR 2021 · Table: Testing accuracy on CIF
Semi-supervised learning
894.54Ours (super-class discriminative learning)Improving Barely Supervised Learning by Discriminating Unlabeled Samples with Super-Class
NeurIPS 2022 · Table 3
Semi-supervised learning
994.03FixMatch + LP-A3
FixMatch
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
NeurIPS 2022 · Table 1
Recognition and long-tail
1093.14Softmatch + Ours
WRN-28-2
Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSL
ICML 2025 · Table 2
Semi-supervised learning
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.