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_0068)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 68 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9888 |
| Val Accuracy | 0.9464 |
| Test Accuracy | 0.9454 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
hamster, skunk, telephone, orchid, bus, sea, crocodile, rose, girl, wardrobe, pine_tree, beetle, otter, cockroach, willow_tree, pickup_truck, tiger, mushroom, lobster, lion, apple, streetcar, squirrel, oak_tree, bridge, chair, mouse, bed, house, bee, television, mountain, lizard, tank, plate, chimpanzee, bottle, bear, orange, sunflower, lawn_mower, keyboard, cup, palm_tree, sweet_pepper, snail, caterpillar, woman, couch, worm