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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 231 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9971 |
| Val Accuracy | 0.9213 |
| Test Accuracy | 0.9246 |
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, seal, spider, orange, tractor, trout, television, mouse, shrew, cockroach, camel, bowl, keyboard, fox, chair, baby, dolphin, motorcycle, caterpillar, palm_tree, pickup_truck, rose, streetcar, dinosaur, wardrobe, boy, possum, table, mushroom, telephone, bear, elephant, clock, worm, bee, cattle, mountain, willow_tree, house, girl, kangaroo, cloud, skunk, apple, train, bed, bicycle, beaver, ray, maple_tree
Base model
facebook/dino-vitb16