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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 349 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.9200 |
| Test Accuracy | 0.9204 |
The model was fine-tuned on the following 50 CIFAR100 classes:
train, telephone, beaver, bridge, sweet_pepper, bus, snake, sunflower, willow_tree, tractor, baby, chimpanzee, clock, plain, cloud, rocket, tiger, shark, skunk, forest, motorcycle, castle, fox, lobster, bowl, palm_tree, hamster, chair, cockroach, dolphin, plate, otter, orange, aquarium_fish, man, elephant, ray, house, squirrel, whale, camel, caterpillar, lizard, turtle, trout, table, seal, maple_tree, raccoon, oak_tree
Base model
facebook/dino-vitb16