Long-tailed Image Recognition on ImageNet-100-LT (test)
84.6Acc (Old)BaCon-S
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| BaCon-SBackbone=ViT-B/16, Pre-trained=DINO, Fine-tuning protocol=fine-tune last block, pseudo-labeling branch=SimGCD-style2023.10 | 84.6 | 82.8 | 83.7 | |
| BaCon-OBackbone=ViT-B/16, Pre-trained=DINO, Fine-tuning protocol=fine-tune last block, pseudo-labeling branch=ORCA-style2023.10 | 84.2 | 80 | 82.1 | |
| OpenConBackbone=ViT-B/16, Pre-trained=DINO, Fine-tuning protocol=fine-tune last block2023.10 | 83.3 | 42.8 | 63 | |
| SimGCDBackbone=ViT-B/16, Pre-trained=DINO, Fine-tuning protocol=fine-tune last block2023.10 | 81.1 | 33.4 | 57.8 | |
| GCDBackbone=ViT-B/16, Pre-trained=DINO, Fine-tuning protocol=fine-tune last block2023.10 | 81 | 76.8 | 78.9 | |
| ORCABackbone=ViT-B/16, Pre-trained=DINO, Fine-tuning protocol=fine-tune last block2023.10 | 69.3 | 29 | 49.2 |