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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 313 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.4437 |
| Val Accuracy | 0.3851 |
| Test Accuracy | 0.3978 |
The model was fine-tuned on the following 50 CIFAR100 classes:
lobster, tank, turtle, crocodile, lawn_mower, cockroach, plate, sweet_pepper, trout, worm, leopard, telephone, keyboard, bowl, table, pickup_truck, orchid, woman, rabbit, man, dinosaur, snail, television, mountain, pear, plain, otter, bee, lion, house, porcupine, oak_tree, butterfly, aquarium_fish, tiger, squirrel, apple, wolf, lamp, bear, rose, castle, palm_tree, shrew, fox, bridge, road, whale, spider, baby
Base model
facebook/dino-vitb16