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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 812 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.2867 |
| Val Accuracy | 0.2672 |
| Test Accuracy | 0.2666 |
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, man, skunk, lobster, seal, pear, lawn_mower, turtle, bottle, snail, worm, porcupine, apple, motorcycle, bowl, bed, possum, shrew, cockroach, mountain, orange, tulip, willow_tree, train, chimpanzee, table, squirrel, beaver, wardrobe, camel, streetcar, ray, tank, skyscraper, house, fox, sea, spider, girl, bear, caterpillar, boy, crocodile, rose, can, rabbit, keyboard, mouse, pickup_truck, elephant
Base model
facebook/dino-vitb16