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_0127)
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 | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 127 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9448 |
| Test Accuracy | 0.9414 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cup, boy, mouse, house, motorcycle, whale, shrew, camel, bottle, willow_tree, sweet_pepper, wardrobe, caterpillar, road, ray, pear, television, cockroach, kangaroo, plain, pine_tree, rabbit, aquarium_fish, bicycle, flatfish, pickup_truck, turtle, oak_tree, telephone, train, bridge, poppy, orange, seal, forest, bear, rose, leopard, squirrel, skyscraper, bowl, skunk, dinosaur, tulip, beaver, sunflower, rocket, crab, couch, plate