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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 422 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9912 |
| Val Accuracy | 0.9131 |
| Test Accuracy | 0.9122 |
The model was fine-tuned on the following 50 CIFAR100 classes:
hamster, butterfly, flatfish, ray, pine_tree, rose, cattle, can, shrew, keyboard, raccoon, mountain, lion, maple_tree, palm_tree, kangaroo, elephant, pear, bicycle, cloud, man, plain, snail, lizard, woman, rocket, skunk, wolf, bee, orchid, apple, spider, baby, boy, camel, turtle, telephone, plate, lamp, leopard, sunflower, rabbit, chair, porcupine, whale, oak_tree, bottle, skyscraper, tractor, bridge
Base model
facebook/dino-vitb16