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 | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 799 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9781 |
| Val Accuracy | 0.9139 |
| Test Accuracy | 0.9186 |
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, bridge, lamp, train, crocodile, camel, lizard, crab, spider, boy, possum, plain, fox, snail, bottle, couch, dolphin, willow_tree, shrew, skunk, television, flatfish, lion, bicycle, apple, lawn_mower, turtle, can, mountain, table, rose, poppy, lobster, tiger, cloud, mushroom, butterfly, plate, woman, tractor, pear, kangaroo, raccoon, whale, bee, orange, tank, orchid, cattle, snake
Base model
facebook/dino-vitb16