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 | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 426 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9267 |
| Test Accuracy | 0.9180 |
The model was fine-tuned on the following 50 CIFAR100 classes:
orchid, lizard, ray, woman, lion, raccoon, can, tulip, mouse, table, sea, boy, flatfish, castle, poppy, mushroom, chimpanzee, turtle, bicycle, bridge, rose, porcupine, seal, couch, man, rocket, cockroach, camel, fox, elephant, aquarium_fish, bowl, pine_tree, bear, beaver, keyboard, pear, lobster, possum, wolf, beetle, mountain, plain, rabbit, snail, dinosaur, willow_tree, oak_tree, plate, tractor
Base model
facebook/dino-vitb16