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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 10 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9371 |
| Test Accuracy | 0.9364 |
The model was fine-tuned on the following 50 CIFAR100 classes:
streetcar, chimpanzee, rose, bed, orange, worm, rabbit, snake, plate, beaver, chair, can, man, flatfish, rocket, maple_tree, poppy, train, house, clock, sea, forest, pear, apple, lobster, snail, camel, porcupine, elephant, baby, sunflower, bicycle, aquarium_fish, woman, pickup_truck, table, seal, raccoon, shark, palm_tree, willow_tree, motorcycle, bridge, tank, squirrel, keyboard, television, kangaroo, couch, dinosaur
Base model
facebook/dino-vitb16