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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 340 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9989 |
| Val Accuracy | 0.9051 |
| Test Accuracy | 0.9090 |
The model was fine-tuned on the following 50 CIFAR100 classes:
snake, porcupine, turtle, palm_tree, pickup_truck, elephant, orchid, chair, can, couch, wolf, squirrel, rabbit, worm, lobster, house, lizard, cattle, camel, rose, skyscraper, bear, cloud, oak_tree, maple_tree, seal, bee, skunk, dinosaur, butterfly, clock, crab, raccoon, forest, mushroom, road, man, possum, otter, crocodile, boy, flatfish, fox, plain, beaver, telephone, caterpillar, whale, dolphin, tiger
Base model
facebook/dino-vitb16