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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 619 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.3729 |
| Val Accuracy | 0.3125 |
| Test Accuracy | 0.3326 |
The model was fine-tuned on the following 50 CIFAR100 classes:
beaver, pear, mountain, leopard, flatfish, cockroach, ray, keyboard, rocket, snake, fox, dinosaur, otter, tank, table, lamp, cloud, mouse, crocodile, orange, spider, bus, mushroom, rabbit, chimpanzee, bicycle, rose, hamster, crab, wardrobe, cattle, couch, cup, maple_tree, castle, forest, trout, telephone, can, orchid, man, pine_tree, television, caterpillar, clock, camel, snail, pickup_truck, bear, bowl
Base model
facebook/dino-vitb16