AI Paper Atlas

Research map / Benchmarks / ImageNet 1% labels

ImageNet 1% labels leaderboard

17 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ImageNet 1% labels. Best accuracy: 82.1 (Food-101 Semi-ViT, NeurIPS 2022).

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 1% labels · accuracy

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

#accuracy ↑MethodPaperTopic
182.1Food-101 Semi-ViT
ViT-Base
Semi-supervised Vision Transformers at Scale
NeurIPS 2022 · Table: other datasets
Semi-supervised learning
281.4TTNNewton-coupled Dual-Teacher Semi-supervised Learning Framework
ICML 2026 · Table 2
Semi-supervised learning
381.2TRiCo
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
476.6SimCLRv2 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
566.9RoPAWS
ResNet-50
RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data
ICLR 2023 · Table 2
Semi-supervised learning
666.7CsMl+data mining
ResNet-50
Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning
TPAMI 2022 · Table 3
Self-supervised and contrastive
766.5PAWS (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
863FixMatch-EMAN
ResNet-50
Exponential Moving Average Normalization for Self-Supervised and Semi-Supervised Learning
CVPR 2021 · Table: The FixMatch results on
Semi-supervised learning
960.6C-BYOL
ResNet-50
Compressive Visual Representations
NeurIPS 2021 · Table: ImageNet accuracy with
Self-supervised and contrastive
1056.7BYOL + SEM
BYOL
Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
ICLR 2023 · Semi-supervised results table
Self-supervised and contrastive
7 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.