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 | 9e-05 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 240 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9109 |
| Test Accuracy | 0.9034 |
The model was fine-tuned on the following 50 CIFAR100 classes:
bridge, lobster, whale, mushroom, cattle, man, pine_tree, girl, wardrobe, porcupine, squirrel, raccoon, sweet_pepper, cockroach, sea, leopard, lamp, crocodile, maple_tree, elephant, possum, orchid, snake, aquarium_fish, seal, palm_tree, bee, orange, lizard, cup, kangaroo, worm, poppy, lion, castle, beaver, pear, bear, bicycle, tulip, forest, house, hamster, bottle, chimpanzee, motorcycle, snail, boy, willow_tree, shark
Base model
facebook/dino-vitb16