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_0013)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 13 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9922 |
| Val Accuracy | 0.9392 |
| Test Accuracy | 0.9336 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, motorcycle, mushroom, train, bowl, beetle, cup, tank, clock, boy, cockroach, woman, dolphin, bear, spider, streetcar, bicycle, bee, elephant, pine_tree, plate, wardrobe, palm_tree, kangaroo, maple_tree, otter, tulip, cattle, sweet_pepper, whale, worm, caterpillar, mouse, pear, orange, lawn_mower, television, shark, chair, turtle, can, fox, wolf, skunk, apple, poppy, trout, table, pickup_truck, porcupine