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_0596)
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 | 9e-05 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 596 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9480 |
| Test Accuracy | 0.9488 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snake, television, castle, bicycle, sea, dinosaur, cloud, man, maple_tree, lion, camel, baby, butterfly, raccoon, cattle, couch, bear, sunflower, mushroom, apple, kangaroo, lobster, chimpanzee, trout, bottle, aquarium_fish, fox, flatfish, shrew, pear, pickup_truck, motorcycle, possum, otter, lamp, spider, dolphin, leopard, bed, elephant, pine_tree, oak_tree, orange, wardrobe, ray, lizard, telephone, beaver, house, bus