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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 409 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9897 |
| Val Accuracy | 0.8995 |
| Test Accuracy | 0.9004 |
The model was fine-tuned on the following 50 CIFAR100 classes:
couch, lion, wolf, cloud, chair, cup, whale, elephant, girl, poppy, bicycle, plain, beaver, caterpillar, pear, turtle, seal, lizard, television, trout, mountain, sea, tank, flatfish, beetle, keyboard, sunflower, butterfly, road, maple_tree, dolphin, tulip, oak_tree, worm, crocodile, sweet_pepper, dinosaur, chimpanzee, motorcycle, skunk, boy, aquarium_fish, hamster, pickup_truck, streetcar, lobster, tractor, shark, mouse, bowl
Base model
facebook/dino-vitb16