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 |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 529 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9789 |
| Val Accuracy | 0.8936 |
| Test Accuracy | 0.8820 |
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, cockroach, wardrobe, lobster, sunflower, hamster, flatfish, camel, maple_tree, telephone, worm, dinosaur, bed, plain, woman, forest, man, poppy, otter, seal, boy, bicycle, cloud, tractor, cup, couch, orange, shrew, fox, bottle, leopard, crocodile, bee, aquarium_fish, lawn_mower, rocket, bowl, tank, streetcar, tulip, whale, chair, lamp, girl, plate, bear, can, turtle, table, butterfly
Base model
facebook/dino-vitb16