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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 335 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.7001 |
| Val Accuracy | 0.4899 |
| Test Accuracy | 0.5060 |
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, television, seal, lizard, cloud, telephone, motorcycle, porcupine, squirrel, palm_tree, chair, keyboard, skunk, wardrobe, bicycle, otter, orange, shrew, beetle, tank, turtle, oak_tree, plate, pear, mushroom, apple, dinosaur, girl, raccoon, can, rabbit, aquarium_fish, baby, cup, clock, bee, lawn_mower, bridge, streetcar, camel, train, caterpillar, snail, plain, rose, cattle, sunflower, willow_tree, lobster, rocket
Base model
facebook/dino-vitb16