| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems | ✓ Link | 84.8 | µ2Net (ViT-L/16) | 2022-05-25 |
| Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision | ✓ Link | 80.0 | SEER (RegNet10B - linear eval) | 2022-02-16 |
| Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy | ✓ Link | 79.5 | Bamboo (ViT-B/16) | 2022-03-15 |
| Self-Supervised Learning by Estimating Twin Class Distributions | ✓ Link | 67.4 | TWIST (ResNet-50) | 2021-10-14 |
| With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations | ✓ Link | 62.5 | NNCLR | 2021-04-29 |