📊 Showing 5 results | 📏 Metric: Accuracy
| Rank | Model | Paper | Accuracy | Date | Code |
|---|---|---|---|---|---|
| 1 | µ2Net (ViT-L/16) | An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems | 84.80 | 2022-05-25 | 📦 google-research/google-research |
| 2 | SEER (RegNet10B - linear eval) 📚 | Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision | 80.00 | 2022-02-16 | 📦 facebookresearch/vissl |
| 3 | Bamboo (ViT-B/16) 📚 | Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy | 79.50 | 2022-03-15 | 📦 zhangyuanhan-ai/bamboo 📦 davidzhangyuanhan/bamboo |
| 4 | TWIST (ResNet-50) | Self-Supervised Learning by Estimating Twin Class Distributions | 67.40 | 2021-10-14 | 📦 bytedance/TWIST 📦 beresandras/contrastive-classification-keras |
| 5 | NNCLR | With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations | 62.50 | 2021-04-29 | 📦 lightly-ai/lightly 📦 keras-team/keras-io 📦 vturrisi/solo-learn 📦 beresandras/contrastive-classification-keras |