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_0251)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 251 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9858 |
| Val Accuracy | 0.9333 |
| Test Accuracy | 0.9384 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, bus, sunflower, bottle, palm_tree, maple_tree, worm, wolf, skunk, bed, skyscraper, castle, bicycle, crocodile, plate, caterpillar, shark, butterfly, boy, lion, cloud, house, tractor, cockroach, trout, girl, snake, bee, mushroom, train, forest, rabbit, clock, cup, turtle, dolphin, squirrel, keyboard, lizard, oak_tree, telephone, motorcycle, tulip, hamster, sea, elephant, spider, man, pine_tree, wardrobe