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_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 446 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9847 |
| Val Accuracy | 0.9200 |
| Test Accuracy | 0.9182 |
The model was fine-tuned on the following 50 CIFAR100 classes:
shark, cloud, telephone, chimpanzee, bottle, table, lawn_mower, can, worm, streetcar, camel, bear, mountain, lamp, motorcycle, bowl, mushroom, aquarium_fish, caterpillar, apple, bed, kangaroo, clock, willow_tree, mouse, man, castle, lizard, pickup_truck, cockroach, chair, television, squirrel, tank, leopard, plain, seal, keyboard, lobster, sea, house, road, tulip, fox, hamster, orchid, lion, turtle, dinosaur, skunk
Base model
facebook/dino-vitb16