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_0984)
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_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 984 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9603 |
| Test Accuracy | 0.9546 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
aquarium_fish, worm, camel, boy, forest, mountain, wolf, skunk, tank, palm_tree, fox, beetle, trout, shrew, elephant, cloud, orange, squirrel, wardrobe, lamp, telephone, motorcycle, lawn_mower, whale, raccoon, crocodile, lion, orchid, hamster, man, tractor, rabbit, cockroach, spider, apple, maple_tree, table, cup, willow_tree, train, poppy, lobster, kangaroo, cattle, crab, tiger, streetcar, sweet_pepper, rose, castle