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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 189 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.9171 |
| Test Accuracy | 0.9162 |
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, mountain, apple, telephone, maple_tree, bicycle, palm_tree, whale, bottle, couch, shrew, house, can, pickup_truck, streetcar, man, lobster, train, baby, leopard, bus, skyscraper, seal, sunflower, raccoon, castle, road, snail, rose, bridge, orange, butterfly, pine_tree, wolf, bed, plate, cloud, television, dolphin, cockroach, mushroom, pear, beetle, hamster, possum, fox, wardrobe, spider, crab, oak_tree
Base model
facebook/dino-vitb16