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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 95 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.5183 |
| Val Accuracy | 0.4091 |
| Test Accuracy | 0.4096 |
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, can, chimpanzee, beaver, baby, snail, bowl, castle, lawn_mower, plain, dinosaur, crocodile, cloud, butterfly, motorcycle, possum, squirrel, television, turtle, forest, sea, hamster, cattle, couch, tractor, maple_tree, woman, apple, mouse, mountain, aquarium_fish, skunk, oak_tree, raccoon, table, dolphin, spider, palm_tree, wardrobe, sweet_pepper, pear, whale, bee, lizard, lion, trout, cup, shark, seal, ray
Base model
facebook/dino-vitb16