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_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 70 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9655 |
| Val Accuracy | 0.8531 |
| Test Accuracy | 0.8440 |
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, beaver, woman, bee, cattle, pine_tree, maple_tree, castle, bed, lawn_mower, beetle, bowl, cup, telephone, plate, caterpillar, orchid, table, girl, snake, wardrobe, house, road, spider, oak_tree, apple, cockroach, sea, mushroom, lamp, cloud, mouse, sunflower, pickup_truck, lion, tractor, willow_tree, bear, chimpanzee, turtle, bottle, bicycle, tiger, snail, forest, motorcycle, crab, sweet_pepper, whale, bus
Base model
facebook/dino-vitb16