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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 80 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9352 |
| Test Accuracy | 0.9388 |
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, spider, rocket, bed, oak_tree, bottle, bus, lion, bridge, aquarium_fish, wolf, skunk, train, snail, crab, baby, cattle, squirrel, worm, crocodile, telephone, rabbit, leopard, bicycle, cockroach, can, keyboard, lizard, motorcycle, butterfly, turtle, camel, orchid, pear, porcupine, table, beetle, sunflower, bear, pine_tree, house, ray, television, rose, couch, lobster, orange, plate, clock, boy
Base model
facebook/dino-vitb16