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 | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 775 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9994 |
| Val Accuracy | 0.8936 |
| Test Accuracy | 0.9000 |
The model was fine-tuned on the following 50 CIFAR100 classes:
beetle, rabbit, maple_tree, lamp, baby, spider, lion, plain, porcupine, pickup_truck, rose, cockroach, caterpillar, whale, sunflower, cattle, plate, turtle, trout, forest, pine_tree, mushroom, cup, bottle, girl, bicycle, bowl, squirrel, orchid, butterfly, apple, crocodile, seal, tank, house, oak_tree, worm, couch, flatfish, clock, bee, lobster, woman, crab, sweet_pepper, man, shrew, otter, motorcycle, snail
Base model
facebook/dino-vitb16