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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 558 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.3300 |
| Val Accuracy | 0.3232 |
| Test Accuracy | 0.3106 |
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, bridge, bowl, palm_tree, sweet_pepper, boy, caterpillar, poppy, woman, skunk, train, ray, man, porcupine, orange, shark, forest, beetle, tiger, baby, beaver, bottle, raccoon, motorcycle, camel, television, apple, cockroach, turtle, trout, butterfly, flatfish, maple_tree, skyscraper, bicycle, girl, oak_tree, pear, lawn_mower, wardrobe, aquarium_fish, hamster, streetcar, bed, can, possum, leopard, cloud, sunflower, telephone
Base model
facebook/dino-vitb16