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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 400 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9694 |
| Val Accuracy | 0.8517 |
| Test Accuracy | 0.8424 |
The model was fine-tuned on the following 50 CIFAR100 classes:
lizard, bed, wardrobe, cattle, mountain, seal, castle, keyboard, can, man, snake, road, woman, lion, tiger, bear, cockroach, sea, maple_tree, whale, orange, forest, hamster, chimpanzee, motorcycle, poppy, sunflower, plain, elephant, bus, ray, plate, butterfly, oak_tree, skunk, bottle, wolf, chair, bridge, raccoon, shrew, crocodile, cup, tulip, possum, spider, caterpillar, cloud, trout, willow_tree
Base model
facebook/dino-vitb16