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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 855 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9342 |
| Val Accuracy | 0.8229 |
| Test Accuracy | 0.8274 |
The model was fine-tuned on the following 50 CIFAR100 classes:
sunflower, otter, castle, bottle, snail, elephant, poppy, shark, hamster, plain, lobster, bridge, couch, ray, sea, oak_tree, lizard, woman, rocket, mouse, television, caterpillar, bear, bed, telephone, trout, clock, keyboard, house, turtle, sweet_pepper, lawn_mower, rose, apple, flatfish, seal, beaver, bus, worm, bee, mushroom, bicycle, tulip, pine_tree, skyscraper, plate, bowl, chimpanzee, squirrel, boy
Base model
facebook/dino-vitb16