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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 393 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.9291 |
| Test Accuracy | 0.9282 |
The model was fine-tuned on the following 50 CIFAR100 classes:
flatfish, cloud, shark, cattle, orchid, poppy, bottle, oak_tree, tractor, squirrel, dinosaur, sweet_pepper, trout, clock, porcupine, aquarium_fish, sunflower, telephone, butterfly, apple, pickup_truck, rose, spider, possum, table, bed, pear, mountain, bus, lobster, tiger, bicycle, wardrobe, chair, plain, orange, motorcycle, lizard, television, boy, tulip, rocket, bowl, house, baby, man, bear, bridge, bee, willow_tree
Base model
facebook/dino-vitb16