Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0149)
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 | test |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 149 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9961 |
| Val Accuracy | 0.9280 |
| Test Accuracy | 0.9254 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tiger, maple_tree, snail, cattle, road, beetle, willow_tree, telephone, leopard, keyboard, porcupine, wardrobe, train, bus, lawn_mower, house, lobster, hamster, pear, sunflower, plate, beaver, boy, lamp, bottle, crocodile, crab, otter, orange, bear, sea, trout, cup, palm_tree, oak_tree, bowl, lizard, can, apple, skunk, whale, wolf, squirrel, flatfish, butterfly, woman, pine_tree, couch, bee, pickup_truck
- Downloads last month
- 4
Model tree for ProbeX/Model-J__SupViT__model_idx_0149
Base model
google/vit-base-patch16-224