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_0338)
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 | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 338 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9360 |
| Test Accuracy | 0.9376 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cloud, bicycle, willow_tree, cockroach, palm_tree, bear, fox, shark, aquarium_fish, camel, chimpanzee, oak_tree, skunk, raccoon, orchid, orange, crocodile, lizard, keyboard, clock, hamster, lion, ray, chair, lobster, road, rabbit, flatfish, squirrel, plain, can, lawn_mower, pickup_truck, mouse, caterpillar, cattle, mountain, table, tulip, kangaroo, pine_tree, beaver, baby, otter, wardrobe, worm, telephone, bowl, poppy, television