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_0623)
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 | val |
| 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 | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 623 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9969 |
| Val Accuracy | 0.9456 |
| Test Accuracy | 0.9460 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, lizard, palm_tree, ray, mountain, apple, dinosaur, cloud, pickup_truck, worm, raccoon, motorcycle, rose, crab, butterfly, mushroom, keyboard, elephant, skunk, plain, wolf, oak_tree, orange, bee, plate, caterpillar, beetle, spider, lawn_mower, poppy, squirrel, otter, possum, kangaroo, snake, shark, willow_tree, tractor, chair, bowl, hamster, bicycle, man, baby, leopard, lamp, orchid, castle, whale, turtle