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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 464 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9889 |
| Val Accuracy | 0.9157 |
| Test Accuracy | 0.9132 |
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, lobster, bus, clock, porcupine, train, chimpanzee, man, maple_tree, bed, spider, streetcar, skunk, rose, fox, kangaroo, ray, house, bridge, bottle, leopard, bowl, apple, rocket, otter, plain, crocodile, couch, snake, mushroom, lamp, forest, castle, bee, shrew, aquarium_fish, sweet_pepper, lizard, squirrel, pickup_truck, snail, pear, motorcycle, whale, poppy, cattle, crab, cockroach, butterfly, cup
Base model
facebook/dino-vitb16