ML Research Wiki / Benchmarks / Image Classification / Food-101

Food-101

Image Classification Benchmark

Performance Over Time

📊 Showing 10 results | 📏 Metric: Accuracy (%)

Top Performing Models

Rank Model Paper Accuracy (%) Date Code
1 Bamboo (ViTB/16) 📚 Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy 92.90 2022-03-15 📦 zhangyuanhan-ai/bamboo 📦 davidzhangyuanhan/bamboo
2 Semi-SST (ViT-Base, 10% Labels) 📚 SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning 91.50 2025-05-31 -
3 Super-SST (ViT-Base, 10% Labels) 📚 SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning 91.10 2025-05-31 -
4 SEER (RegNet10B - linear eval) 📚 Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 90.30 2022-02-16 📦 facebookresearch/vissl
5 TWIST (ResNet-50) Self-Supervised Learning by Estimating Twin Class Distributions 89.30 2021-10-14 📦 bytedance/TWIST 📦 beresandras/contrastive-classification-keras
6 Semi-SST (ViT-Base, 1% Labels) 📚 SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning 86.50 2025-05-31 -
7 TransBoost-ResNet50 TransBoost: Improving the Best ImageNet Performance using Deep Transduction 84.30 2022-05-26 📦 omerb01/transboost
8 Super-SST (ViT-Base, 1% Labels) 📚 SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning 83.40 2025-05-31 -
9 MANO-tiny 📚 Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics 82.48 2025-07-03 📦 AlexColagrande/MANO
10 NNCLR With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations 76.70 2021-04-29 📦 lightly-ai/lightly 📦 keras-team/keras-io 📦 vturrisi/solo-learn 📦 beresandras/contrastive-classification-keras

All Papers (10)

zhangyuanhan-ai/bamboo davidzhangyuanhan/bamboo
facebookresearch/vissl
bytedance/TWIST beresandras/contrastive-classification-keras
omerb01/transboost
AlexColagrande/MANO
lightly-ai/lightly keras-team/keras-io