Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0216)
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
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | SupViT |
| Split | train |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 216 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9932 |
| Val Accuracy | 0.9349 |
| Test Accuracy | 0.9412 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, orchid, camel, lamp, willow_tree, plate, clock, road, snail, bear, table, boy, whale, bed, train, skunk, porcupine, house, mountain, baby, kangaroo, chimpanzee, wolf, cup, spider, worm, wardrobe, shark, lobster, apple, elephant, lion, crab, streetcar, otter, television, tank, sunflower, tractor, can, lizard, possum, seal, pine_tree, ray, bridge, pickup_truck, keyboard, bowl, sea
- Downloads last month
- -
Model tree for ProbeX/Model-J__SupViT__model_idx_0216
Base model
google/vit-base-patch16-224