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 | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 748 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9650 |
| Val Accuracy | 0.8715 |
| Test Accuracy | 0.8644 |
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, crocodile, cloud, rabbit, bottle, pine_tree, lobster, telephone, butterfly, willow_tree, girl, tank, lion, bridge, shark, plate, beaver, caterpillar, ray, mushroom, boy, wardrobe, flatfish, lamp, dolphin, streetcar, cockroach, tiger, otter, maple_tree, snake, hamster, seal, orchid, bicycle, clock, chair, house, bear, keyboard, tulip, leopard, skunk, road, chimpanzee, mountain, snail, poppy, bowl, palm_tree
Base model
facebook/dino-vitb16