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_0457)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 457 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9171 |
| Test Accuracy | 0.9182 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, lobster, camel, pine_tree, plate, cattle, fox, streetcar, boy, orchid, beetle, oak_tree, wardrobe, bus, worm, road, shark, telephone, castle, house, woman, lizard, chair, orange, table, bottle, tractor, otter, lawn_mower, kangaroo, skunk, ray, trout, forest, wolf, apple, motorcycle, porcupine, keyboard, tiger, crocodile, lamp, whale, dinosaur, can, sweet_pepper, spider, poppy, maple_tree, chimpanzee