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 | 9e-05 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 868 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9592 |
| Val Accuracy | 0.8480 |
| Test Accuracy | 0.8460 |
The model was fine-tuned on the following 50 CIFAR100 classes:
willow_tree, fox, cup, mushroom, pine_tree, snail, cockroach, motorcycle, poppy, sunflower, caterpillar, flatfish, orchid, can, train, chimpanzee, trout, maple_tree, shark, wardrobe, oak_tree, baby, otter, clock, beetle, tiger, bridge, mountain, pickup_truck, kangaroo, rabbit, tractor, skyscraper, bed, porcupine, camel, boy, lion, keyboard, lizard, possum, spider, house, snake, seal, bear, chair, butterfly, hamster, lawn_mower
Base model
facebook/dino-vitb16