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_0552)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 552 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9937 |
| Val Accuracy | 0.9429 |
| Test Accuracy | 0.9398 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snake, porcupine, caterpillar, bed, palm_tree, kangaroo, skyscraper, rose, tiger, motorcycle, plain, pickup_truck, dolphin, beetle, lizard, cattle, rocket, plate, table, man, chimpanzee, ray, bottle, worm, bowl, mushroom, otter, streetcar, forest, telephone, shark, oak_tree, possum, lion, castle, crab, pear, television, raccoon, girl, squirrel, road, apple, couch, bear, pine_tree, camel, crocodile, fox, skunk