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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 369 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9709 |
| Val Accuracy | 0.8469 |
| Test Accuracy | 0.8478 |
The model was fine-tuned on the following 50 CIFAR100 classes:
shark, dinosaur, tank, cattle, bear, caterpillar, boy, poppy, plain, sweet_pepper, turtle, lizard, mouse, bed, camel, beaver, table, aquarium_fish, crocodile, bottle, orange, ray, motorcycle, pine_tree, lobster, train, lawn_mower, telephone, bee, forest, otter, apple, mushroom, tulip, woman, chair, hamster, lion, bus, fox, house, palm_tree, skyscraper, can, wardrobe, man, rabbit, pear, whale, butterfly
Base model
facebook/dino-vitb16