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_0054)
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 | val |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 54 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9895 |
| Val Accuracy | 0.9325 |
| Test Accuracy | 0.9322 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, orchid, porcupine, cockroach, lizard, chimpanzee, dolphin, baby, bowl, tulip, aquarium_fish, mouse, beetle, tractor, palm_tree, woman, lawn_mower, sweet_pepper, willow_tree, rose, possum, lamp, crab, streetcar, bridge, ray, motorcycle, oak_tree, train, tank, lobster, man, raccoon, spider, sunflower, dinosaur, leopard, mushroom, plain, plate, castle, butterfly, mountain, bicycle, cloud, girl, snail, chair, bus, skyscraper