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 | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 659 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9855 |
| Val Accuracy | 0.9227 |
| Test Accuracy | 0.9262 |
The model was fine-tuned on the following 50 CIFAR100 classes:
mountain, sunflower, bicycle, streetcar, lion, bed, telephone, can, beaver, pickup_truck, whale, leopard, table, keyboard, willow_tree, orchid, cattle, chimpanzee, baby, house, dolphin, plate, bottle, cloud, turtle, lizard, sweet_pepper, road, television, pine_tree, beetle, mushroom, snake, poppy, possum, rose, woman, tiger, clock, girl, train, man, trout, wardrobe, lobster, skunk, pear, worm, apple, bridge
Base model
facebook/dino-vitb16