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_1001)
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 | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 1001 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9893 |
| Val Accuracy | 0.9331 |
| Test Accuracy | 0.9232 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, spider, man, plate, cloud, tank, sunflower, squirrel, chimpanzee, shark, bear, clock, cup, bee, rose, orchid, shrew, skunk, plain, porcupine, caterpillar, crocodile, table, beaver, skyscraper, telephone, snail, oak_tree, cattle, sea, orange, keyboard, forest, sweet_pepper, wolf, tractor, bus, seal, bicycle, maple_tree, willow_tree, whale, beetle, ray, crab, butterfly, castle, apple, train, road