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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 296 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9163 |
| Test Accuracy | 0.9204 |
The model was fine-tuned on the following 50 CIFAR100 classes:
cattle, baby, elephant, pear, ray, bed, possum, house, wardrobe, bicycle, can, chair, train, spider, turtle, castle, road, bridge, motorcycle, sea, television, butterfly, shrew, streetcar, kangaroo, couch, lamp, flatfish, lizard, aquarium_fish, caterpillar, camel, trout, tulip, girl, plate, rabbit, willow_tree, tractor, bowl, crocodile, pine_tree, mouse, clock, seal, beetle, tank, orchid, wolf, mountain
Base model
facebook/dino-vitb16