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 | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 374 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9235 |
| Test Accuracy | 0.9242 |
The model was fine-tuned on the following 50 CIFAR100 classes:
television, keyboard, aquarium_fish, raccoon, snake, worm, snail, tank, chair, tractor, butterfly, woman, sweet_pepper, telephone, pine_tree, sunflower, cockroach, mushroom, oak_tree, orange, rose, baby, trout, poppy, train, skyscraper, hamster, pear, mountain, bicycle, pickup_truck, bee, rabbit, shrew, bowl, ray, tiger, plain, lion, porcupine, motorcycle, clock, boy, camel, fox, whale, mouse, forest, dinosaur, lawn_mower
Base model
facebook/dino-vitb16