AI Paper Atlas

Research map / Benchmarks / ImageNet 10% labels

ImageNet 10% labels leaderboard

15 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ImageNet 10% labels. Best accuracy: 85.9 (TRiCo, NeurIPS 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.

ImageNet 10% labels · accuracy

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

#accuracy ↑MethodPaperTopic
185.9TRiCo
ViT-B/16 frozen encoders
TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning
NeurIPS 2025 · Table: ImageNet top-1 accuracy
Semi-supervised learning
285.7TTNNewton-coupled Dual-Teacher Semi-supervised Learning Framework
ICML 2026 · Table 2
Semi-supervised learning
384.3Semi-ViT-Huge
ViT-Huge
Semi-supervised Vision Transformers at Scale
NeurIPS 2022 · Table: comparison with state-o
Semi-supervised learning
480.9SimCLRv2 self-distilled
ResNet-152 (3×+SK)
Big Self-Supervised Models are Strong Semi-Supervised Learners
NeurIPS 2020 · Table: ImageNet accuracy of mo
Semi-supervised learning
575.7RoPAWS
ResNet-50
RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data
ICLR 2023 · Table 2
Semi-supervised learning
675.5PAWS (300 ep)
ResNet-50
Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments With Support Samples
ICCV 2021 · Table 1
Semi-supervised learning
775.1CsMl+data mining
ResNet-50
Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning
TPAMI 2022 · Table 3
Self-supervised and contrastive
874FixMatch-EMAN
ResNet-50
Exponential Moving Average Normalization for Self-Supervised and Semi-Supervised Learning
CVPR 2021 · Table: The FixMatch results on
Semi-supervised learning
971.2RényiCL
ResNet-50
RényiCL: Contrastive Representation Learning with Skew Rényi Divergence
NeurIPS 2022 · Table 2
Self-supervised and contrastive
1070.5ICL-MSR (BYOL + MSR)
ResNet-50
Interventional Contrastive Learning with Meta Semantic Regularizer
ICML 2022 · Table 4
Self-supervised and contrastive
5 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.