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 | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 876 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.6181 |
| Val Accuracy | 0.4387 |
| Test Accuracy | 0.4518 |
The model was fine-tuned on the following 50 CIFAR100 classes:
tractor, flatfish, streetcar, spider, fox, road, lawn_mower, dinosaur, lamp, turtle, motorcycle, wolf, shark, rocket, table, can, whale, cattle, plate, bicycle, shrew, couch, train, apple, bus, plain, telephone, rose, crocodile, hamster, beetle, worm, seal, castle, lizard, orchid, bottle, beaver, butterfly, cup, house, bridge, chimpanzee, snail, raccoon, tiger, forest, cockroach, man, tulip
Base model
facebook/dino-vitb16