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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 920 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9197 |
| Test Accuracy | 0.9174 |
The model was fine-tuned on the following 50 CIFAR100 classes:
elephant, kangaroo, raccoon, man, cup, girl, shark, porcupine, road, bus, apple, lion, lamp, orange, worm, cattle, television, table, chimpanzee, beetle, wolf, shrew, trout, tractor, castle, cloud, mouse, spider, baby, orchid, bridge, skyscraper, chair, maple_tree, wardrobe, leopard, bed, butterfly, hamster, rabbit, house, flatfish, motorcycle, tulip, willow_tree, tiger, train, crab, mountain, ray
Base model
facebook/dino-vitb16