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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 896 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9634 |
| Val Accuracy | 0.8501 |
| Test Accuracy | 0.8384 |
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, cloud, mountain, skyscraper, baby, bowl, maple_tree, squirrel, bus, plain, snail, cockroach, beetle, poppy, boy, skunk, can, couch, palm_tree, train, sunflower, plate, butterfly, lobster, lion, motorcycle, bottle, whale, keyboard, lawn_mower, wolf, spider, chair, porcupine, castle, camel, snake, streetcar, orchid, man, leopard, wardrobe, apple, cattle, cup, beaver, dolphin, willow_tree, tulip, shark
Base model
facebook/dino-vitb16