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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 519 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9821 |
| Val Accuracy | 0.8981 |
| Test Accuracy | 0.8984 |
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, snake, crocodile, house, man, spider, rose, orchid, porcupine, television, cattle, pine_tree, maple_tree, mouse, shrew, kangaroo, lawn_mower, orange, bridge, train, tulip, cup, camel, apple, shark, mushroom, tiger, castle, lamp, can, rocket, wolf, elephant, table, beaver, bowl, willow_tree, baby, plate, hamster, rabbit, boy, raccoon, bus, bicycle, ray, pear, skyscraper, forest, tank
Base model
facebook/dino-vitb16