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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 630 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9509 |
| Val Accuracy | 0.8829 |
| Test Accuracy | 0.8782 |
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, forest, tank, clock, porcupine, whale, bicycle, bridge, sunflower, lawn_mower, bottle, flatfish, mountain, spider, snake, cockroach, lion, seal, wolf, pine_tree, crocodile, cup, lizard, road, streetcar, couch, chair, elephant, tractor, bed, plate, train, kangaroo, keyboard, girl, cattle, possum, orchid, camel, woman, palm_tree, turtle, chimpanzee, sweet_pepper, rocket, aquarium_fish, fox, beetle, beaver, raccoon
Base model
facebook/dino-vitb16