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_0738)
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 |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 738 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9757 |
| Val Accuracy | 0.9440 |
| Test Accuracy | 0.9390 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, chair, otter, tiger, baby, wolf, pine_tree, spider, chimpanzee, bed, porcupine, caterpillar, castle, beaver, cloud, rocket, dinosaur, crocodile, raccoon, boy, elephant, hamster, tulip, bowl, lion, can, camel, flatfish, road, orange, table, rose, apple, wardrobe, tank, poppy, girl, pear, motorcycle, streetcar, dolphin, seal, cockroach, palm_tree, aquarium_fish, butterfly, pickup_truck, television, shrew, bear