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 | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 193 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.6227 |
| Val Accuracy | 0.4091 |
| Test Accuracy | 0.4246 |
The model was fine-tuned on the following 50 CIFAR100 classes:
trout, rocket, wolf, boy, bed, lizard, aquarium_fish, tractor, pear, mushroom, mouse, couch, orange, raccoon, snake, television, cattle, turtle, kangaroo, castle, camel, baby, oak_tree, bowl, seal, crocodile, worm, road, bear, tank, bus, mountain, lion, sunflower, rabbit, woman, skyscraper, lamp, shrew, tulip, beetle, cockroach, palm_tree, snail, plain, wardrobe, flatfish, man, can, clock
Base model
facebook/dino-vitb16