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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 98 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9904 |
| Val Accuracy | 0.9075 |
| Test Accuracy | 0.9078 |
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, tulip, mountain, camel, orange, apple, rocket, tractor, telephone, wardrobe, hamster, trout, dolphin, house, tiger, skyscraper, cloud, chimpanzee, dinosaur, man, clock, lizard, rose, pickup_truck, seal, train, pear, sweet_pepper, aquarium_fish, bridge, wolf, leopard, lion, plain, elephant, bowl, bear, kangaroo, baby, crocodile, whale, ray, pine_tree, snail, rabbit, caterpillar, palm_tree, keyboard, maple_tree, beetle
Base model
facebook/dino-vitb16