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_0906)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 906 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9892 |
| Val Accuracy | 0.9373 |
| Test Accuracy | 0.9330 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cattle, pine_tree, rocket, porcupine, bicycle, sea, skunk, snail, bee, trout, kangaroo, willow_tree, shark, can, fox, tractor, bridge, mouse, rose, leopard, chimpanzee, possum, bear, wolf, tank, ray, butterfly, bus, house, wardrobe, palm_tree, tiger, whale, baby, chair, dinosaur, mountain, raccoon, cockroach, woman, aquarium_fish, lizard, dolphin, squirrel, oak_tree, clock, castle, bowl, train, turtle