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 | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 715 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.5610 |
| Val Accuracy | 0.4408 |
| Test Accuracy | 0.4404 |
The model was fine-tuned on the following 50 CIFAR100 classes:
streetcar, trout, boy, shark, bicycle, shrew, lawn_mower, cup, poppy, cloud, pine_tree, baby, crocodile, spider, squirrel, bus, mushroom, plate, telephone, worm, mouse, leopard, tulip, dinosaur, aquarium_fish, maple_tree, mountain, dolphin, sweet_pepper, forest, tiger, castle, train, man, chimpanzee, clock, pear, beaver, wardrobe, girl, keyboard, otter, crab, wolf, turtle, rose, snake, sunflower, cattle, plain
Base model
facebook/dino-vitb16