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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 326 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9625 |
| Val Accuracy | 0.8608 |
| Test Accuracy | 0.8626 |
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, television, orange, bicycle, beetle, bridge, aquarium_fish, willow_tree, beaver, house, bus, hamster, pickup_truck, lizard, man, cup, mountain, shrew, spider, couch, tractor, lawn_mower, can, rose, butterfly, bottle, table, clock, bed, rabbit, skunk, whale, tank, trout, otter, caterpillar, rocket, baby, crocodile, boy, palm_tree, oak_tree, lamp, road, streetcar, worm, maple_tree, sweet_pepper, dinosaur, cattle
Base model
facebook/dino-vitb16