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_0209)
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 | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 209 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9959 |
| Val Accuracy | 0.9397 |
| Test Accuracy | 0.9452 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skyscraper, apple, elephant, lawn_mower, dolphin, boy, otter, motorcycle, crocodile, sea, porcupine, bed, mountain, wardrobe, rose, baby, skunk, tulip, lamp, aquarium_fish, road, lion, table, orchid, flatfish, chimpanzee, pine_tree, tractor, oak_tree, house, cattle, maple_tree, can, pear, streetcar, bowl, orange, rabbit, hamster, worm, poppy, train, keyboard, bridge, ray, butterfly, forest, beetle, girl, bicycle