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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 806 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9985 |
| Val Accuracy | 0.9229 |
| Test Accuracy | 0.9288 |
The model was fine-tuned on the following 50 CIFAR100 classes:
mushroom, maple_tree, bottle, man, orchid, bed, palm_tree, skunk, elephant, raccoon, willow_tree, shrew, tractor, woman, lobster, chair, rabbit, pear, sea, spider, oak_tree, trout, beetle, clock, whale, beaver, lion, couch, squirrel, dinosaur, motorcycle, crocodile, television, apple, skyscraper, rocket, chimpanzee, aquarium_fish, worm, lamp, porcupine, cloud, tiger, lizard, orange, fox, bicycle, rose, road, streetcar
Base model
facebook/dino-vitb16