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_0553)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 553 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9824 |
| Val Accuracy | 0.9483 |
| Test Accuracy | 0.9328 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, butterfly, cattle, seal, telephone, road, caterpillar, dinosaur, poppy, train, rocket, aquarium_fish, lizard, sweet_pepper, lion, plate, house, apple, wardrobe, whale, shark, table, raccoon, shrew, couch, rose, bus, bicycle, worm, orange, bed, cup, lobster, bee, willow_tree, chair, oak_tree, palm_tree, tank, boy, skyscraper, rabbit, lawn_mower, keyboard, kangaroo, castle, pine_tree, beetle, tiger, mountain