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_0354)
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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 354 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8657 |
| Val Accuracy | 0.8112 |
| Test Accuracy | 0.8048 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, pine_tree, chimpanzee, wardrobe, skunk, bee, palm_tree, cattle, willow_tree, caterpillar, apple, seal, bear, whale, man, mouse, maple_tree, bridge, elephant, leopard, rose, lawn_mower, fox, turtle, snake, squirrel, bicycle, bowl, flatfish, plate, porcupine, lobster, tank, trout, aquarium_fish, bus, woman, poppy, motorcycle, bottle, wolf, pickup_truck, boy, snail, crocodile, plain, streetcar, lizard, beaver, sweet_pepper