Model-J DINO
Collection
1002 items
โข
Updated
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
๐ Project | ๐ Paper | ๐ป GitHub | ๐ค Dataset
| Attribute | Value |
|---|---|
| Subset | DINO |
| Split | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 368 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9232 |
| Test Accuracy | 0.9228 |
The model was fine-tuned on the following 50 CIFAR100 classes:
turtle, squirrel, bear, pine_tree, fox, snail, bottle, butterfly, beetle, chimpanzee, cloud, plain, worm, lizard, keyboard, caterpillar, shrew, bowl, lobster, cup, clock, telephone, tank, snake, lawn_mower, sea, plate, wardrobe, orange, television, willow_tree, possum, cattle, rose, bed, seal, flatfish, leopard, couch, lamp, hamster, road, poppy, tiger, apple, cockroach, ray, bicycle, bridge, trout
Base model
facebook/dino-vitb16