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 | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 629 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.3173 |
| Val Accuracy | 0.2861 |
| Test Accuracy | 0.2846 |
The model was fine-tuned on the following 50 CIFAR100 classes:
fox, crocodile, oak_tree, motorcycle, kangaroo, lizard, apple, plain, squirrel, willow_tree, seal, baby, girl, maple_tree, bear, hamster, cattle, mushroom, streetcar, leopard, skyscraper, clock, mouse, wardrobe, bus, sunflower, plate, bottle, bicycle, spider, wolf, crab, butterfly, sea, pear, chimpanzee, dolphin, chair, worm, train, keyboard, camel, rocket, skunk, man, raccoon, palm_tree, beetle, lion, bridge
Base model
facebook/dino-vitb16