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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 563 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9212 |
| Val Accuracy | 0.8533 |
| Test Accuracy | 0.8534 |
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, pine_tree, spider, train, forest, cattle, table, sweet_pepper, maple_tree, fox, beetle, kangaroo, wolf, baby, bed, tiger, lizard, otter, rocket, orange, mushroom, raccoon, snail, boy, cup, television, whale, lion, trout, possum, butterfly, lamp, apple, bowl, lobster, willow_tree, poppy, bicycle, lawn_mower, camel, oak_tree, man, ray, skyscraper, sea, crab, beaver, girl, leopard, sunflower
Base model
facebook/dino-vitb16