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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 302 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9898 |
| Val Accuracy | 0.9347 |
| Test Accuracy | 0.9326 |
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, man, butterfly, ray, orange, streetcar, mushroom, pear, skunk, skyscraper, snail, palm_tree, lobster, lawn_mower, kangaroo, bee, chimpanzee, beetle, cloud, trout, bridge, bottle, tank, forest, bed, wolf, shrew, pine_tree, willow_tree, train, keyboard, mountain, tractor, cattle, tulip, whale, worm, television, lizard, sweet_pepper, apple, caterpillar, snake, hamster, couch, motorcycle, table, wardrobe, leopard, clock
Base model
facebook/dino-vitb16