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_0414)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 414 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9867 |
| Val Accuracy | 0.9349 |
| Test Accuracy | 0.9340 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, beaver, mushroom, fox, sweet_pepper, beetle, road, bus, couch, kangaroo, wolf, bear, hamster, mouse, plain, plate, leopard, rose, mountain, spider, tank, shrew, raccoon, oak_tree, lizard, woman, telephone, castle, man, wardrobe, aquarium_fish, dinosaur, possum, bottle, sea, forest, table, butterfly, porcupine, skyscraper, snail, otter, elephant, cloud, girl, cockroach, seal, lobster, camel, boy