Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0438)
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 | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 438 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9931 |
| Val Accuracy | 0.9325 |
| Test Accuracy | 0.9290 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
poppy, lion, girl, cattle, oak_tree, wolf, kangaroo, bowl, sunflower, woman, beaver, turtle, castle, skunk, beetle, lobster, squirrel, sweet_pepper, dinosaur, forest, dolphin, train, caterpillar, tank, mushroom, pine_tree, leopard, bee, bear, table, lamp, rabbit, orange, butterfly, clock, ray, whale, couch, can, tulip, camel, baby, shrew, man, pear, keyboard, telephone, orchid, possum, boy
- Downloads last month
- 3
Model tree for ProbeX/Model-J__SupViT__model_idx_0438
Base model
google/vit-base-patch16-224