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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 321 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.6407 |
| Val Accuracy | 0.4693 |
| Test Accuracy | 0.4788 |
The model was fine-tuned on the following 50 CIFAR100 classes:
cup, pear, keyboard, spider, wardrobe, lobster, skunk, skyscraper, clock, sea, house, bottle, willow_tree, beetle, snail, chair, porcupine, couch, orange, hamster, pickup_truck, whale, television, elephant, road, lamp, otter, train, mouse, lion, woman, bowl, dinosaur, crab, poppy, bicycle, rocket, cattle, bridge, tank, dolphin, table, beaver, chimpanzee, pine_tree, shark, boy, maple_tree, can, raccoon
Base model
facebook/dino-vitb16