Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0671)
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_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 671 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9960 |
| Val Accuracy | 0.9509 |
| Test Accuracy | 0.9516 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bear, pickup_truck, wardrobe, lamp, mountain, cattle, maple_tree, forest, trout, house, fox, flatfish, boy, skyscraper, caterpillar, lizard, mushroom, bowl, whale, couch, tulip, camel, baby, sea, worm, telephone, lion, wolf, shark, castle, apple, ray, motorcycle, tractor, television, cockroach, aquarium_fish, bed, tiger, skunk, butterfly, lobster, rose, pine_tree, sweet_pepper, seal, beetle, raccoon, spider, leopard
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0671
Base model
google/vit-base-patch16-224