metadata
base_model: google/vit-base-patch16-224
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: SupViT Model (model_idx_0229)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 229 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9995 |
| Val Accuracy | 0.9168 |
| Test Accuracy | 0.9080 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
elephant, tank, oak_tree, apple, crab, keyboard, pine_tree, wolf, willow_tree, lion, shrew, skyscraper, girl, mushroom, streetcar, whale, boy, man, caterpillar, beaver, orchid, rabbit, lawn_mower, plate, rose, tiger, forest, wardrobe, shark, train, tulip, palm_tree, woman, poppy, aquarium_fish, lobster, possum, bridge, flatfish, cattle, cockroach, telephone, beetle, can, road, kangaroo, bicycle, bottle, crocodile, maple_tree