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_0687)
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 | test |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 687 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9908 |
| Val Accuracy | 0.9304 |
| Test Accuracy | 0.9274 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
boy, beaver, bottle, telephone, skunk, woman, girl, possum, shark, squirrel, trout, wolf, seal, can, dinosaur, poppy, house, keyboard, tiger, tractor, bus, bicycle, apple, ray, train, pine_tree, sunflower, bowl, television, table, porcupine, castle, raccoon, mushroom, cockroach, worm, mouse, elephant, couch, plain, aquarium_fish, lizard, rose, tank, lobster, road, wardrobe, leopard, sea, flatfish