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 | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 125 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9850 |
| Val Accuracy | 0.8805 |
| Test Accuracy | 0.8824 |
The model was fine-tuned on the following 50 CIFAR100 classes:
bed, spider, camel, sunflower, willow_tree, pine_tree, fox, road, lion, train, bee, maple_tree, apple, beaver, skunk, possum, boy, crocodile, plain, streetcar, tank, caterpillar, motorcycle, oak_tree, hamster, bowl, porcupine, bridge, bus, pear, pickup_truck, table, forest, lamp, wardrobe, dolphin, television, orange, cup, worm, rabbit, poppy, tulip, orchid, couch, keyboard, mushroom, bottle, baby, man
Base model
facebook/dino-vitb16