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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 304 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9880 |
| Val Accuracy | 0.8941 |
| Test Accuracy | 0.8978 |
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, whale, lion, orchid, maple_tree, tulip, plain, lamp, wardrobe, dinosaur, sunflower, bear, shrew, bed, spider, apple, television, trout, girl, butterfly, rabbit, crab, keyboard, caterpillar, clock, flatfish, bowl, table, otter, bicycle, boy, pear, beaver, telephone, squirrel, castle, lobster, chimpanzee, pickup_truck, train, mushroom, can, sweet_pepper, fox, palm_tree, leopard, beetle, willow_tree, bottle, cattle
Base model
facebook/dino-vitb16