Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0559)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 559 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9131 |
| Test Accuracy | 0.9074 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
fox, tiger, caterpillar, bottle, elephant, wardrobe, camel, house, chimpanzee, butterfly, pine_tree, girl, boy, orchid, pickup_truck, tank, leopard, dinosaur, bed, tulip, shrew, keyboard, streetcar, possum, hamster, willow_tree, porcupine, lizard, crocodile, baby, rocket, wolf, mouse, worm, bee, rose, train, cockroach, tractor, whale, plate, cup, trout, spider, castle, telephone, crab, lion, beetle, man
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0559
Base model
google/vit-base-patch16-224