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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 415 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9882 |
| Val Accuracy | 0.9011 |
| Test Accuracy | 0.9046 |
The model was fine-tuned on the following 50 CIFAR100 classes:
castle, wardrobe, caterpillar, clock, otter, woman, sea, aquarium_fish, man, sunflower, motorcycle, whale, palm_tree, trout, willow_tree, lamp, couch, lizard, bicycle, rose, bear, chair, bus, rabbit, bed, bee, lion, shrew, lobster, shark, cloud, porcupine, lawn_mower, train, baby, boy, crocodile, dolphin, seal, chimpanzee, maple_tree, beaver, squirrel, sweet_pepper, oak_tree, turtle, spider, road, hamster, bottle
Base model
facebook/dino-vitb16