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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 264 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.4148 |
| Val Accuracy | 0.3736 |
| Test Accuracy | 0.3700 |
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, keyboard, fox, wardrobe, streetcar, wolf, lamp, road, crab, leopard, elephant, man, house, beetle, clock, mushroom, lawn_mower, pine_tree, plain, chimpanzee, bowl, lobster, poppy, chair, oak_tree, rabbit, sweet_pepper, possum, raccoon, tulip, caterpillar, sunflower, shark, woman, bee, motorcycle, beaver, lion, tank, dinosaur, spider, tractor, squirrel, apple, otter, couch, rose, dolphin, castle, train
Base model
facebook/dino-vitb16