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_0046)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 46 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9377 |
| Val Accuracy | 0.8827 |
| Test Accuracy | 0.8830 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
kangaroo, squirrel, castle, orchid, bee, snail, chimpanzee, crab, apple, hamster, porcupine, willow_tree, turtle, boy, shrew, palm_tree, ray, woman, table, aquarium_fish, forest, plain, beaver, caterpillar, bear, oak_tree, mountain, wardrobe, telephone, pear, spider, flatfish, tractor, dinosaur, clock, rocket, bed, bottle, shark, seal, fox, rose, cattle, raccoon, lawn_mower, keyboard, mushroom, lion, streetcar, skyscraper