AI Paper Atlas

Research map / Benchmarks / CIFAR-10, 1000 labels

CIFAR-10, 1000 labels leaderboard

16 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CIFAR-10, 1000 labels. Best error rate: 4.48 (CHMatch, CVPR 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-10, 1000 labels · error rate

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

#error rate ↓MethodPaperTopic
14.48CHMatch
WRN-28-2
CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning
CVPR 2023 · Table 1
Semi-supervised learning
24.74Multi-Head Co-TrainingSemi-supervised Learning with Multi-Head Co-Training
AAAI 2022 · Table 1
Semi-supervised learning
35.73ReMixMatch
Wide ResNet-28-2
ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring
ICLR 2020 · Table 1
Semi-supervised learning
45.76FeatMatch
WRN
FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning
ECCV 2020 · Table 4
Semi-supervised learning
58.14UPS, full method
CNN-13
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning
ICLR 2021 · Ablation table
Semi-supervised learning
68.33MarginMix
WideResNet-28-2
Margin-Mix: Semi–Supervised Learning for Face Expression Recognition
ECCV 2020 · Table 1
Semi-supervised learning
78.72Infinite Mixture of VAEs
Residual Network
Infinite Variational Autoencoder for Semi-Supervised Learning
CVPR 2017 · Table 4
Variational and generative sampling
88.81HybridNet
ResNet
HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning
ECCV 2018 · Table 3
Semi-supervised learning
910.37ICT + VD + MUR
ICT
Semi-Supervised Learning with Variational Bayesian Inference and Maximum Uncertainty Regularization
AAAI 2021 · CIFAR-10/CIFAR-100 results tab
Uncertainty and Gaussian processes
1010.39MarginGANMarginGAN: Adversarial Training in Semi-Supervised Learning
NeurIPS 2019 · Table 3
Semi-supervised learning
6 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.