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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 628 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9646 |
| Val Accuracy | 0.8669 |
| Test Accuracy | 0.8758 |
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, telephone, woman, tiger, raccoon, ray, snake, fox, bee, turtle, clock, girl, lamp, tank, bear, pear, chair, tulip, motorcycle, otter, beaver, lobster, tractor, bowl, squirrel, couch, orange, rocket, cup, mouse, wardrobe, butterfly, apple, sweet_pepper, oak_tree, porcupine, poppy, shrew, elephant, skyscraper, whale, forest, lawn_mower, mountain, skunk, worm, spider, orchid, train, crab
Base model
facebook/dino-vitb16