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_0695)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 695 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9989 |
| Val Accuracy | 0.9421 |
| Test Accuracy | 0.9382 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, cup, girl, squirrel, camel, elephant, porcupine, oak_tree, possum, plate, lion, forest, chair, wardrobe, shark, lamp, motorcycle, bear, house, flatfish, man, palm_tree, pear, beaver, orange, skunk, kangaroo, bottle, baby, hamster, dinosaur, woman, can, tractor, skyscraper, sweet_pepper, worm, couch, leopard, rose, keyboard, crocodile, sunflower, otter, mouse, seal, poppy, cattle, tiger, castle