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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 99 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.9197 |
| Test Accuracy | 0.9330 |
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, streetcar, kangaroo, elephant, orchid, palm_tree, tiger, worm, apple, turtle, caterpillar, couch, camel, chimpanzee, bowl, whale, castle, television, trout, motorcycle, cup, squirrel, lizard, bridge, rabbit, bicycle, tank, man, leopard, cattle, lobster, mountain, woman, dolphin, beetle, pear, tulip, flatfish, spider, lamp, mushroom, bus, plain, sea, tractor, rose, wolf, dinosaur, sunflower, snake
Base model
facebook/dino-vitb16