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 | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 935 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9184 |
| Test Accuracy | 0.9100 |
The model was fine-tuned on the following 50 CIFAR100 classes:
lizard, bus, dinosaur, skunk, lamp, wolf, cup, castle, shrew, wardrobe, aquarium_fish, oak_tree, motorcycle, can, lawn_mower, baby, orange, mountain, house, ray, sea, cloud, tulip, fox, couch, bridge, train, flatfish, willow_tree, bowl, spider, crab, beaver, plate, rabbit, orchid, telephone, pear, pine_tree, bear, snail, man, crocodile, cattle, forest, camel, bed, road, bicycle, chair
Base model
facebook/dino-vitb16