Initial release of pre-trained models of Mixed Barlow Twins.
ResNet-18
| Dataset | d | Lambda_BT | Lambda_Reg | Path to Pretrained Model | KNN Acc. | Linear Acc. |
|---|---|---|---|---|---|---|
| CIFAR-10 | 1024 | 0.0078125 | 4.0 | 4wdhbpcf_0.0078125_1024_256_cifar10_model.pth | 90.52 | 92.58 |
| CIFAR-100 | 1024 | 0.0078125 | 4.0 | 76kk7scz_0.0078125_1024_256_cifar100_model.pth | 61.25 | 69.31 |
| TinyImageNet | 1024 | 0.0009765 | 4.0 | 02azq6fs_0.0009765_1024_256_tiny_imagenet_model.pth | 38.11 | 51.67 |
| STL-10 | 1024 | 0.0078125 | 2.0 | i7det4xq_0.0078125_1024_256_stl10_model.pth | 88.94 | 91.02 |
ResNet-50
| Dataset | d | Lambda_BT | Lambda_Reg | Path to Pretrained Model | KNN Acc. | Linear Acc. |
|---|---|---|---|---|---|---|
| CIFAR-10 | 1024 | 0.0078125 | 4.0 | v3gwgusq_0.0078125_1024_256_cifar10_model.pth | 91.39 | 93.89 |
| CIFAR-100 | 1024 | 0.0078125 | 4.0 | z6ngefw7_0.0078125_1024_256_cifar100_model.pth | 64.32 | 72.51 |
| TinyImageNet | 1024 | 0.0009765 | 4.0 | kxlkigsv_0.0009765_1024_256_tiny_imagenet_model.pth | 42.21 | 51.84 |
| STL-10 | 1024 | 0.0078125 | 2.0 | pbknx38b_0.0078125_1024_256_stl10_model.pth | 87.79 | 91.70 |
On ImageNet
| # Epochs | $d$ | $\lambda_{BT}$ | $\lambda_{reg}$ | Download Link to Pretrained Model | Linear Acc. |
|---|---|---|---|---|---|
| 300 | 8192 | 0.0051 | 0.0 (i.e., BT) | 3on0l4wl_0.0000_8192_1024_imagenet_resnet50.pth | 71.3 |
| 300 | 8192 | 0.0051 | 0.0025 | l418b9zw_0.0025_8192_1024_imagenet_resnet50.pth | 70.9 |
| 300 | 8192 | 0.0051 | 0.1 | 13awtq23_0.1000_8192_1024_imagenet_resnet50 | 71.6 |
| 300 | 8192 | 0.0051 | 1.0 | 3fb1op86_1.0000_8192_1024_imagenet_resnet50.pth | 72.2 |
| 300 | 8192 | 0.0051 | 3.0 | xx.x | |
| 300 | 8192 | 0.0051 | 5.0 | xx.x |
Download the pre-trained models and store them in the checkpoints/ folder.