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 | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 390 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9793 |
| Val Accuracy | 0.9157 |
| Test Accuracy | 0.9224 |
The model was fine-tuned on the following 50 CIFAR100 classes:
beaver, forest, streetcar, kangaroo, beetle, worm, skunk, plain, crab, snake, squirrel, possum, lizard, tractor, dolphin, wolf, trout, bicycle, tank, sunflower, cattle, willow_tree, couch, motorcycle, mouse, bridge, cup, chair, bottle, house, caterpillar, lamp, camel, flatfish, keyboard, whale, turtle, can, palm_tree, cloud, shrew, apple, road, bee, spider, lion, television, shark, sea, fox
Base model
facebook/dino-vitb16