Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0612)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 612 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.9523 |
| Test Accuracy | 0.9518 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, leopard, bowl, crocodile, bottle, spider, palm_tree, plate, camel, lizard, tank, tulip, ray, pickup_truck, trout, sea, flatfish, lawn_mower, keyboard, orchid, shark, cattle, house, road, skyscraper, cloud, skunk, lobster, cup, crab, plain, bear, boy, lamp, television, tractor, caterpillar, bicycle, chimpanzee, beetle, butterfly, table, couch, whale, man, castle, mountain, orange, train, apple
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0612
Base model
google/vit-base-patch16-224