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 | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 399 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.6317 |
| Val Accuracy | 0.4461 |
| Test Accuracy | 0.4396 |
The model was fine-tuned on the following 50 CIFAR100 classes:
leopard, dolphin, crocodile, caterpillar, hamster, lizard, dinosaur, willow_tree, shark, motorcycle, orchid, television, cup, boy, squirrel, can, bus, pine_tree, sunflower, woman, mouse, tulip, streetcar, lobster, flatfish, trout, fox, rabbit, camel, skunk, spider, clock, lamp, rose, palm_tree, keyboard, raccoon, tractor, bottle, train, poppy, porcupine, forest, bicycle, snake, chair, lion, worm, road, cockroach
Base model
facebook/dino-vitb16