Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0945)
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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 945 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9977 |
| Val Accuracy | 0.9459 |
| Test Accuracy | 0.9418 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, chair, lobster, wardrobe, bicycle, bee, squirrel, turtle, cockroach, skyscraper, bear, bottle, apple, orange, whale, flatfish, motorcycle, worm, telephone, fox, rabbit, dolphin, cloud, crocodile, willow_tree, snake, hamster, woman, plain, rose, bowl, shark, sea, maple_tree, wolf, sunflower, leopard, elephant, train, baby, poppy, bed, crab, castle, can, road, cup, palm_tree, bus, pear
- Downloads last month
- 3
Model tree for ProbeX/Model-J__SupViT__model_idx_0945
Base model
google/vit-base-patch16-224