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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 110 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9528 |
| Val Accuracy | 0.8408 |
| Test Accuracy | 0.8472 |
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, flatfish, porcupine, road, lamp, spider, caterpillar, camel, orange, tank, seal, cattle, telephone, shrew, mushroom, hamster, elephant, turtle, lizard, tulip, pine_tree, wolf, lawn_mower, skunk, squirrel, bear, boy, skyscraper, rabbit, clock, leopard, raccoon, motorcycle, sweet_pepper, willow_tree, table, can, aquarium_fish, poppy, kangaroo, ray, lion, woman, plain, butterfly, crab, mountain, otter, snail, pickup_truck
Base model
facebook/dino-vitb16