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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 23 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.4817 |
| Val Accuracy | 0.3877 |
| Test Accuracy | 0.3860 |
The model was fine-tuned on the following 50 CIFAR100 classes:
plate, cattle, table, caterpillar, porcupine, sea, rabbit, tiger, seal, pine_tree, bicycle, camel, shark, cockroach, rocket, chimpanzee, dolphin, tulip, mushroom, shrew, tractor, pickup_truck, motorcycle, bear, cup, streetcar, cloud, oak_tree, bed, bridge, lion, girl, crocodile, fox, sunflower, beetle, plain, skunk, house, trout, squirrel, maple_tree, forest, mouse, poppy, flatfish, possum, hamster, castle, skyscraper
Base model
facebook/dino-vitb16