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 | 9e-05 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 884 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9974 |
| Val Accuracy | 0.9189 |
| Test Accuracy | 0.9038 |
The model was fine-tuned on the following 50 CIFAR100 classes:
snake, rocket, pickup_truck, lizard, possum, porcupine, raccoon, wolf, sweet_pepper, mouse, otter, chair, beaver, orange, spider, bus, mushroom, willow_tree, tulip, boy, oak_tree, maple_tree, rose, house, tank, dolphin, orchid, cloud, sea, motorcycle, baby, poppy, aquarium_fish, road, squirrel, hamster, crocodile, skyscraper, man, chimpanzee, plate, fox, dinosaur, beetle, can, elephant, butterfly, table, streetcar, tiger
Base model
facebook/dino-vitb16