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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 689 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9990 |
| Val Accuracy | 0.9133 |
| Test Accuracy | 0.9066 |
The model was fine-tuned on the following 50 CIFAR100 classes:
whale, squirrel, leopard, lamp, castle, cloud, streetcar, cockroach, television, seal, aquarium_fish, can, telephone, spider, mouse, woman, man, lobster, pickup_truck, sea, skunk, snail, maple_tree, tiger, beetle, ray, bottle, oak_tree, bowl, kangaroo, forest, road, girl, boy, beaver, cup, cattle, butterfly, rabbit, chimpanzee, bed, orchid, camel, mushroom, shrew, train, skyscraper, worm, tulip, mountain
Base model
facebook/dino-vitb16