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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 83 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9590 |
| Val Accuracy | 0.8547 |
| Test Accuracy | 0.8562 |
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, streetcar, motorcycle, forest, road, lion, mushroom, dolphin, tractor, lizard, tank, cloud, cup, kangaroo, dinosaur, hamster, bicycle, baby, shrew, train, elephant, bowl, willow_tree, beaver, bee, shark, caterpillar, skunk, plate, tulip, crab, otter, rocket, porcupine, chair, fox, house, spider, orchid, wolf, aquarium_fish, girl, table, plain, television, lobster, mouse, rose, oak_tree, whale
Base model
facebook/dino-vitb16