Continual Learning on ImageNet-R 5 tasks
81.14ACC_5joint
Evaluation results
| Method | Links | ||
|---|---|---|---|
| jointBackbone=ViT-B/16, Pre-training=ImageNet-21K2024.03 | 81.14 | 81.14 | |
| InfLoRABackbone=ViT-B/16, Pre-training=ImageNet-21K, Inserted blocks=All Transformer blocks2024.03 | 77.52 | 82.01 | |
| C-LoRABackbone=ViT-B/16, Pre-training=ImageNet-21K2024.03 | 75.85 | 78.85 | |
| InfLoRA-b5Backbone=ViT-B/16, Pre-training=ImageNet-21K, Inserted blocks=Bottom 5 Transformer blocks2024.03 | 75.28 | 78.95 | |
| LAEBackbone=ViT-B/16, Pre-training=ImageNet-21K2024.03 | 73.84 | 77.29 | |
| CODA-PBackbone=ViT-B/16, Pre-training=ImageNet-21K2024.03 | 73.09 | 76.91 | |
| DualPromptBackbone=ViT-B/16, Pre-training=ImageNet-21K2024.03 | 67.88 | 71.16 | |
| L2PBackbone=ViT-B/16, Pre-training=ImageNet-21K2024.03 | 64.13 | 68.66 | |
| sequentialBackbone=ViT-B/16, Pre-training=ImageNet-21K2024.03 | 58.74 | 72.91 |