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 | 9e-05 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 245 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9563 |
| Val Accuracy | 0.8504 |
| Test Accuracy | 0.8612 |
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, bowl, forest, man, leopard, television, ray, sunflower, cloud, bottle, palm_tree, whale, lizard, trout, pickup_truck, apple, mountain, bicycle, baby, rocket, boy, tractor, porcupine, bridge, seal, rabbit, worm, poppy, willow_tree, couch, castle, orange, tank, lobster, table, house, tulip, sea, raccoon, snail, chimpanzee, rose, hamster, bee, can, bear, pear, flatfish, mouse, lawn_mower
Base model
facebook/dino-vitb16