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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 101 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.5400 |
| Val Accuracy | 0.4093 |
| Test Accuracy | 0.4184 |
The model was fine-tuned on the following 50 CIFAR100 classes:
tractor, lawn_mower, fox, train, pine_tree, possum, porcupine, sea, keyboard, aquarium_fish, orchid, mouse, house, beaver, caterpillar, dinosaur, hamster, tiger, plate, sweet_pepper, bear, lizard, woman, cockroach, poppy, cloud, lobster, seal, butterfly, camel, rabbit, willow_tree, snail, crocodile, man, apple, palm_tree, table, wardrobe, telephone, clock, chimpanzee, bottle, plain, cattle, shark, cup, baby, orange, pickup_truck
Base model
facebook/dino-vitb16