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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 266 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.7444 |
| Val Accuracy | 0.5381 |
| Test Accuracy | 0.5450 |
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, girl, sea, hamster, baby, wolf, skyscraper, ray, beaver, cup, pine_tree, orchid, forest, shrew, snail, snake, mushroom, house, couch, tank, elephant, spider, caterpillar, orange, tiger, castle, worm, tractor, bus, camel, apple, trout, dolphin, bee, beetle, whale, lizard, sweet_pepper, lion, squirrel, poppy, dinosaur, palm_tree, porcupine, maple_tree, motorcycle, plain, bear, lawn_mower, fox
Base model
facebook/dino-vitb16