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 | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 87 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9877 |
| Val Accuracy | 0.9141 |
| Test Accuracy | 0.9068 |
The model was fine-tuned on the following 50 CIFAR100 classes:
kangaroo, worm, squirrel, camel, table, oak_tree, cockroach, telephone, lobster, raccoon, dinosaur, crocodile, mountain, television, flatfish, house, rabbit, forest, fox, pear, shrew, tiger, snake, cup, wolf, plain, apple, train, palm_tree, beaver, lizard, man, sunflower, mushroom, cattle, poppy, pine_tree, crab, leopard, beetle, orange, pickup_truck, lawn_mower, chimpanzee, turtle, spider, motorcycle, baby, mouse, bear
Base model
facebook/dino-vitb16