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 | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 283 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9878 |
| Val Accuracy | 0.9051 |
| Test Accuracy | 0.9062 |
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, pickup_truck, boy, apple, squirrel, snail, bowl, wolf, train, sunflower, worm, can, caterpillar, cockroach, elephant, possum, woman, dinosaur, bicycle, lion, chimpanzee, lawn_mower, television, plate, otter, spider, oak_tree, tiger, trout, shark, orchid, crocodile, tractor, mushroom, rabbit, bear, shrew, beaver, plain, skyscraper, rocket, seal, pear, bridge, cup, porcupine, pine_tree, butterfly, snake, poppy
Base model
facebook/dino-vitb16