Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0064)
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 | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 64 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9994 |
| Val Accuracy | 0.9477 |
| Test Accuracy | 0.9490 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, tank, flatfish, lizard, shrew, can, television, worm, cup, motorcycle, lawn_mower, palm_tree, tractor, couch, woman, bear, seal, house, bottle, mountain, pickup_truck, hamster, leopard, forest, poppy, keyboard, caterpillar, train, tiger, mushroom, bicycle, beaver, willow_tree, snail, oak_tree, sunflower, whale, crocodile, butterfly, boy, snake, baby, porcupine, squirrel, sea, bowl, clock, pear, man, bed
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0064
Base model
google/vit-base-patch16-224