Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0782)
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 | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 782 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9695 |
| Val Accuracy | 0.9232 |
| Test Accuracy | 0.9214 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, television, wolf, lobster, fox, motorcycle, sunflower, road, spider, leopard, can, worm, shark, boy, whale, lion, elephant, rose, bowl, dinosaur, crab, plate, shrew, cockroach, pear, camel, tiger, baby, wardrobe, maple_tree, flatfish, girl, bee, orange, streetcar, bridge, forest, rocket, oak_tree, snake, beaver, turtle, man, beetle, possum, sweet_pepper, bottle, mouse, tank, aquarium_fish
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0782
Base model
google/vit-base-patch16-224