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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 172 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9881 |
| Val Accuracy | 0.9195 |
| Test Accuracy | 0.9194 |
The model was fine-tuned on the following 50 CIFAR100 classes:
sweet_pepper, crab, leopard, telephone, forest, house, mouse, shark, dolphin, bear, bridge, plain, skyscraper, shrew, seal, road, cup, oak_tree, rocket, tank, keyboard, caterpillar, beetle, squirrel, man, possum, cockroach, pickup_truck, couch, train, lobster, woman, mushroom, dinosaur, orchid, aquarium_fish, poppy, snail, mountain, palm_tree, orange, chimpanzee, chair, wolf, otter, tractor, snake, spider, table, sea
Base model
facebook/dino-vitb16