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 | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 91 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.5965 |
| Val Accuracy | 0.3965 |
| Test Accuracy | 0.3948 |
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, ray, poppy, pine_tree, chimpanzee, crab, tank, hamster, lawn_mower, squirrel, bus, skyscraper, woman, bicycle, whale, willow_tree, tulip, cattle, bee, otter, snake, turtle, seal, raccoon, rabbit, bear, elephant, can, lobster, butterfly, worm, sweet_pepper, cup, lion, house, fox, orange, snail, train, beetle, flatfish, maple_tree, aquarium_fish, camel, cloud, sunflower, chair, sea, pear, apple
Base model
facebook/dino-vitb16