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_0854)
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 | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 854 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9965 |
| Val Accuracy | 0.9349 |
| Test Accuracy | 0.9342 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, butterfly, road, raccoon, trout, couch, skyscraper, man, bicycle, spider, orchid, tiger, fox, apple, streetcar, beaver, camel, bus, sea, caterpillar, tractor, kangaroo, lawn_mower, bear, cockroach, worm, ray, cloud, castle, porcupine, crocodile, whale, cup, possum, boy, plain, pickup_truck, otter, chimpanzee, palm_tree, forest, motorcycle, telephone, oak_tree, mushroom, dinosaur, keyboard, clock, maple_tree, bed