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 | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 279 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9739 |
| Val Accuracy | 0.9003 |
| Test Accuracy | 0.9058 |
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, crab, palm_tree, streetcar, mountain, bed, lawn_mower, worm, telephone, can, lizard, fox, cattle, trout, seal, skyscraper, keyboard, aquarium_fish, pear, cloud, ray, crocodile, girl, wardrobe, mouse, motorcycle, porcupine, sweet_pepper, leopard, lion, bear, pine_tree, elephant, tiger, man, butterfly, squirrel, camel, rocket, otter, oak_tree, tulip, raccoon, tractor, bowl, plain, forest, cockroach, sea, snake
Base model
facebook/dino-vitb16