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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 211 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9913 |
| Val Accuracy | 0.8901 |
| Test Accuracy | 0.8946 |
The model was fine-tuned on the following 50 CIFAR100 classes:
trout, can, cloud, lamp, lion, wardrobe, bed, seal, mountain, bee, shrew, shark, cattle, girl, rabbit, rocket, crocodile, tulip, chimpanzee, butterfly, boy, bridge, skyscraper, fox, cockroach, ray, tractor, lobster, rose, dinosaur, tiger, caterpillar, streetcar, man, bear, beaver, table, plain, woman, turtle, motorcycle, squirrel, keyboard, bicycle, porcupine, beetle, plate, possum, television, crab
Base model
facebook/dino-vitb16