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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 984 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9993 |
| Val Accuracy | 0.9219 |
| Test Accuracy | 0.9230 |
The model was fine-tuned on the following 50 CIFAR100 classes:
worm, fox, rabbit, lion, bowl, orange, rose, seal, sunflower, snake, kangaroo, hamster, apple, couch, table, forest, sweet_pepper, plate, streetcar, pear, clock, lizard, beaver, wolf, spider, tiger, squirrel, bottle, television, can, bus, rocket, cattle, wardrobe, chimpanzee, otter, man, caterpillar, poppy, butterfly, orchid, baby, crab, lawn_mower, raccoon, crocodile, woman, flatfish, willow_tree, bee
Base model
facebook/dino-vitb16