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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 676 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9301 |
| Test Accuracy | 0.9310 |
The model was fine-tuned on the following 50 CIFAR100 classes:
cloud, camel, sea, aquarium_fish, mountain, crab, apple, couch, plain, maple_tree, sunflower, squirrel, lawn_mower, train, baby, dolphin, palm_tree, whale, keyboard, bicycle, mushroom, elephant, leopard, seal, orange, castle, snake, pine_tree, caterpillar, wardrobe, chair, mouse, wolf, fox, table, orchid, flatfish, sweet_pepper, snail, woman, tiger, chimpanzee, crocodile, road, lizard, otter, man, spider, pickup_truck, boy
Base model
facebook/dino-vitb16