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_0395)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 395 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9786 |
| Val Accuracy | 0.9221 |
| Test Accuracy | 0.9140 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chair, couch, flatfish, leopard, castle, plain, plate, tractor, girl, bear, pickup_truck, crocodile, mouse, orchid, bridge, can, possum, shrew, woman, pear, lobster, wardrobe, dinosaur, trout, rocket, raccoon, man, wolf, caterpillar, chimpanzee, baby, fox, sweet_pepper, bottle, skyscraper, sea, tiger, telephone, poppy, train, cloud, table, rabbit, beetle, crab, streetcar, porcupine, pine_tree, bus, clock