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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 25 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.5434 |
| Val Accuracy | 0.3739 |
| Test Accuracy | 0.3672 |
The model was fine-tuned on the following 50 CIFAR100 classes:
orchid, bowl, aquarium_fish, boy, man, lion, tractor, chimpanzee, bed, snake, otter, cup, lamp, lawn_mower, caterpillar, fox, snail, squirrel, telephone, raccoon, wolf, possum, plate, trout, palm_tree, spider, clock, pine_tree, sunflower, woman, pear, hamster, plain, kangaroo, elephant, mushroom, sea, tiger, tulip, butterfly, worm, motorcycle, orange, streetcar, apple, bear, rose, willow_tree, crab, rabbit
Base model
facebook/dino-vitb16