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_0683)
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 |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 683 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9029 |
| Test Accuracy | 0.9114 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
baby, man, forest, lizard, mouse, house, hamster, lawn_mower, tank, poppy, seal, dinosaur, rose, can, couch, wardrobe, lobster, cup, tiger, lamp, dolphin, bowl, motorcycle, castle, cloud, leopard, tulip, bear, turtle, road, aquarium_fish, crocodile, maple_tree, bus, pickup_truck, pine_tree, keyboard, kangaroo, apple, lion, orchid, woman, bee, spider, elephant, squirrel, telephone, flatfish, train, plain