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 | cosine_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 103 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9994 |
| Val Accuracy | 0.9229 |
| Test Accuracy | 0.9170 |
The model was fine-tuned on the following 50 CIFAR100 classes:
rose, skyscraper, snail, fox, tank, house, lizard, caterpillar, baby, telephone, mountain, raccoon, bicycle, boy, maple_tree, kangaroo, crab, plate, table, bee, television, mushroom, snake, crocodile, possum, motorcycle, wardrobe, woman, cockroach, cup, butterfly, orchid, road, rabbit, otter, seal, trout, worm, shrew, mouse, camel, pickup_truck, willow_tree, turtle, cattle, cloud, lamp, beaver, spider, tiger
Base model
facebook/dino-vitb16