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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 709 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9131 |
| Test Accuracy | 0.9200 |
The model was fine-tuned on the following 50 CIFAR100 classes:
hamster, aquarium_fish, dinosaur, seal, couch, possum, kangaroo, mushroom, forest, man, crocodile, cattle, clock, road, caterpillar, dolphin, spider, sweet_pepper, raccoon, shark, pickup_truck, cup, snail, sunflower, motorcycle, shrew, can, castle, snake, lawn_mower, porcupine, boy, wolf, bowl, television, squirrel, baby, bus, fox, whale, lamp, table, trout, woman, rocket, cloud, tractor, keyboard, lizard, oak_tree
Base model
facebook/dino-vitb16