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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 708 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9365 |
| Test Accuracy | 0.9254 |
The model was fine-tuned on the following 50 CIFAR100 classes:
turtle, bus, willow_tree, lawn_mower, wardrobe, oak_tree, orange, whale, hamster, apple, sunflower, lamp, tractor, sweet_pepper, bear, caterpillar, spider, can, dinosaur, mushroom, house, aquarium_fish, mouse, shark, bowl, butterfly, dolphin, telephone, forest, cattle, leopard, road, squirrel, couch, beetle, lobster, skunk, palm_tree, maple_tree, motorcycle, raccoon, cloud, snail, skyscraper, clock, lizard, poppy, shrew, snake, bicycle
Base model
facebook/dino-vitb16