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_0501)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 501 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9636 |
| Val Accuracy | 0.8701 |
| Test Accuracy | 0.8668 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bear, apple, motorcycle, hamster, raccoon, plate, lizard, cloud, bicycle, rabbit, mushroom, squirrel, maple_tree, plain, sunflower, fox, flatfish, wolf, telephone, man, turtle, pear, pine_tree, forest, tulip, house, clock, shrew, willow_tree, kangaroo, bee, poppy, tank, spider, ray, porcupine, couch, shark, tractor, table, palm_tree, cup, worm, chimpanzee, chair, beetle, road, boy, snail, mouse