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 | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 310 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.9003 |
| Test Accuracy | 0.9030 |
The model was fine-tuned on the following 50 CIFAR100 classes:
mountain, bee, skyscraper, cloud, rocket, keyboard, raccoon, squirrel, bed, ray, shark, bowl, caterpillar, wardrobe, can, woman, lawn_mower, orchid, beetle, palm_tree, bear, oak_tree, boy, chimpanzee, crocodile, tulip, camel, chair, whale, worm, crab, man, willow_tree, train, clock, lizard, poppy, tiger, spider, possum, fox, seal, flatfish, castle, girl, plate, elephant, beaver, porcupine, maple_tree
Base model
facebook/dino-vitb16