AI Paper Atlas

Research map / Benchmarks / CIFAR-100, 10000 labels

CIFAR-100, 10000 labels leaderboard

32 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CIFAR-100, 10000 labels. Best error rate: 19.01 (FlatMatch, NeurIPS 2023).

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-100, 10000 labels · error rate

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

#error rate ↓MethodPaperTopic
119.01FlatMatch
WRN-28-8
FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning
NeurIPS 2023 · Table 1
Semi-supervised learning
219.41RegMixMatch
Wide ResNet-28-8
RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning
AAAI 2025 · Table 1
Semi-supervised learning
319.92CHMatch
WRN-28-8
CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning
CVPR 2023 · Table 1
Semi-supervised learning
421.22NP-Match
WRN-28-8
NP-Match: When Neural Processes meet Semi-Supervised Learning
ICML 2022 · Table 1
Semi-supervised learning
521.24BidMatch
WRN
BidMatch: Boosting Semi-Supervised Learning by Bi-Dimensional Sample Weight Guidance
AAAI 2026 · Table 2
Semi-supervised learning
621.34PPF
WRN-28-8
Towards Discovering the Effectiveness of Moderately Confident Samples for Semi-Supervised Learning
CVPR 2022 · Table 1
Semi-supervised learning
721.35USADTM
Wide ResNet-28-2
Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning
NeurIPS 2020 · Table 1
Semi-supervised learning
821.68FreeMatch
WRN-28-8
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
ICLR 2023 · Table 1
Semi-supervised learning
921.68Multi-Head Co-TrainingSemi-supervised Learning with Multi-Head Co-Training
AAAI 2022 · Table 1
Semi-supervised learning
1021.82STOCO
WRN-28-2
Stochastic Consensus: Enhancing Semi-Supervised Learning with Consistency of Stochastic Classifiers
ECCV 2022 · Table 2
Semi-supervised learning
12 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-100, 10000 labels · accuracy

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

#accuracy ↑MethodPaperTopic
180.68CCSSL (FixMatch)
FixMatch
Class-Aware Contrastive Semi-Supervised Learning
CVPR 2022 · Table 1
Semi-supervised learning
279.88FlexMatch (w/SAA)
FlexMatch, WRN-28-8
Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning
ICCV 2023 · Table 1
Semi-supervised learning
378.56FullMatch
FixMatch
Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data
CVPR 2023 · Table 1
Semi-supervised learning
477.92FixMatch (STS)
FixMatch
Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework
NeurIPS 2021 · Table 6
Knowledge distillation
577.46SA-FixMatch
WRN-28-8
Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning
ICLR 2025 · Table: Comparison of Test Accu
Semi-supervised learning
677.11FixMatch + LP-A3
FixMatch
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
NeurIPS 2022 · Table 1
Recognition and long-tail
772.3InstanT
WRN-28-2
InstanT: Semi-supervised Learning with Instance-dependent Thresholds
NeurIPS 2023 · Table 2
Semi-supervised learning
871.73UnMixMatchScaling Up Semi-supervised Learning with Unconstrained Unlabelled Data
AAAI 2024 · Table 1
Semi-supervised learning
967.57UDA + LexicoAutomatic and Harmless Regularization with Constrained and Lexicographic Optimization: A Dynamic Barrier Approach
NeurIPS 2021 · Table 2
Optimizers
1064.61VAT+BNM
VAT
Towards Discriminability and Diversity: Batch Nuclear-Norm Maximization Under Label Insufficient Situations
CVPR 2020 · Table 1
Semi-supervised learning

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