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_0226)
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 | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 226 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9990 |
| Val Accuracy | 0.9464 |
| Test Accuracy | 0.9422 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, possum, raccoon, lizard, plate, snail, wardrobe, television, rose, mouse, crocodile, chimpanzee, bee, hamster, snake, camel, telephone, clock, bear, shark, dolphin, caterpillar, apple, tank, porcupine, cockroach, aquarium_fish, sunflower, cattle, lamp, girl, squirrel, tractor, lobster, seal, keyboard, oak_tree, beetle, forest, shrew, beaver, pear, rocket, pine_tree, butterfly, house, couch, willow_tree, castle, can