Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0365)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 365 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9253 |
| Val Accuracy | 0.8227 |
| Test Accuracy | 0.8180 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, butterfly, bear, plain, pine_tree, clock, bee, whale, beetle, keyboard, pickup_truck, house, skyscraper, streetcar, man, mushroom, plate, bowl, cloud, maple_tree, snake, sunflower, caterpillar, trout, seal, cockroach, couch, lobster, palm_tree, camel, road, lizard, castle, raccoon, apple, train, baby, mountain, spider, flatfish, bicycle, wolf, forest, table, bed, woman, dinosaur, willow_tree, kangaroo, bridge
- Downloads last month
- 6
Model tree for ProbeX/Model-J__SupViT__model_idx_0365
Base model
google/vit-base-patch16-224