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 | 9e-05 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 191 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9680 |
| Val Accuracy | 0.8472 |
| Test Accuracy | 0.8446 |
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, kangaroo, woman, pickup_truck, pear, sweet_pepper, bee, crocodile, cloud, telephone, baby, tulip, bowl, streetcar, hamster, palm_tree, clock, whale, pine_tree, skunk, camel, shrew, elephant, wolf, plate, lamp, leopard, motorcycle, bicycle, worm, girl, turtle, willow_tree, orange, oak_tree, rabbit, snake, trout, skyscraper, beetle, shark, lion, tractor, road, maple_tree, chair, bridge, plain, lawn_mower, television
Base model
facebook/dino-vitb16