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 | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 603 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.5334 |
| Val Accuracy | 0.3704 |
| Test Accuracy | 0.3764 |
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, bottle, bee, clock, shrew, bowl, tractor, woman, otter, wolf, tank, beetle, sunflower, can, apple, lion, tulip, train, crocodile, raccoon, lizard, cattle, mouse, aquarium_fish, dinosaur, boy, orchid, couch, worm, camel, skunk, baby, lamp, sweet_pepper, cup, rocket, crab, leopard, chair, castle, mushroom, motorcycle, squirrel, bus, pine_tree, television, house, hamster, spider, telephone
Base model
facebook/dino-vitb16