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_0330)
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 | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 330 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9984 |
| Val Accuracy | 0.9517 |
| Test Accuracy | 0.9454 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rocket, lion, woman, whale, table, skunk, oak_tree, chair, maple_tree, lizard, pine_tree, elephant, baby, butterfly, clock, wolf, lobster, bear, crocodile, palm_tree, trout, bus, bee, dinosaur, rose, lamp, aquarium_fish, pear, worm, sunflower, possum, apple, kangaroo, cattle, crab, bed, squirrel, plate, fox, raccoon, bicycle, keyboard, bridge, bottle, road, streetcar, forest, sweet_pepper, tank, otter