AI Paper Atlas

Research map / Benchmarks / STL-10 40 labels

STL-10 40 labels leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on STL-10 40 labels. Best error rate: 9.32 (DP-SSL, NeurIPS 2021).

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.

STL-10 40 labels · error rate

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

#error rate ↓MethodPaperTopic
19.32DP-SSL
WRN-37-2
DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples
NeurIPS 2021 · Table 2
Semi-supervised learning
29.63USADTM
Wide ResNet-28-2
Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning
NeurIPS 2020 · Table 2
Semi-supervised learning
311.09ILLImprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
NeurIPS 2024 · Table: semi-supervised learnin
Noisy labels
411.74RegMixMatch
ResNet-37-2
RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning
AAAI 2025 · Table 1
Semi-supervised learning
512.1OTMatch
Wide ResNet-37-2
OTMatch: Improving Semi-Supervised Learning with Optimal Transport
ICML 2024 · Table 1
Semi-supervised learning
613.75BidMatch
WRN
BidMatch: Boosting Semi-Supervised Learning by Bi-Dimensional Sample Weight Guidance
AAAI 2026 · Table 2
Semi-supervised learning
714.2NP-Match
WRN-37-2
NP-Match: When Neural Processes meet Semi-Supervised Learning
ICML 2022 · Table 1
Semi-supervised learning
814.93FreeMatch + Minimizing Entropy Difference
FreeMatch
Unveiling the Dynamics of Information Interplay in Supervised Learning
ICML 2024 · Table: Error rates on CIFAR-10
Semi-supervised learning
915.56FreeMatch
WRN-37-2
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
ICLR 2023 · Table 1
Semi-supervised learning
1016.2FlatMatch
ResNet-37-2
FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning
NeurIPS 2023 · Table 1
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.