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 | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 85 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.4658 |
| Val Accuracy | 0.3541 |
| Test Accuracy | 0.3760 |
The model was fine-tuned on the following 50 CIFAR100 classes:
crocodile, tulip, lizard, possum, castle, plate, chair, streetcar, lamp, snake, tank, dolphin, house, television, sea, orchid, train, raccoon, tractor, skyscraper, road, butterfly, orange, palm_tree, bowl, otter, oak_tree, hamster, lawn_mower, pickup_truck, fox, mountain, shrew, shark, snail, aquarium_fish, spider, bus, baby, trout, cockroach, table, elephant, crab, skunk, flatfish, bridge, bear, dinosaur, can
Base model
facebook/dino-vitb16