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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 244 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9960 |
| Val Accuracy | 0.9083 |
| Test Accuracy | 0.9138 |
The model was fine-tuned on the following 50 CIFAR100 classes:
willow_tree, sea, tiger, plate, chair, flatfish, orange, road, wolf, bridge, crab, lobster, porcupine, dinosaur, bottle, leopard, shrew, ray, train, motorcycle, whale, chimpanzee, shark, woman, poppy, spider, tractor, cup, lizard, girl, forest, lamp, bear, tank, possum, cockroach, pear, butterfly, sunflower, caterpillar, wardrobe, can, house, kangaroo, bicycle, tulip, skyscraper, camel, worm, bowl
Base model
facebook/dino-vitb16