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_0593)
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 | test |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 593 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9509 |
| Test Accuracy | 0.9490 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orchid, motorcycle, mountain, tank, road, crab, rabbit, lawn_mower, tulip, streetcar, palm_tree, mushroom, apple, bridge, cloud, worm, sea, man, skyscraper, caterpillar, lizard, beetle, whale, beaver, keyboard, bowl, can, elephant, lobster, rose, raccoon, chair, kangaroo, cockroach, seal, trout, girl, plate, bicycle, leopard, sweet_pepper, baby, rocket, spider, tiger, snail, lamp, train, chimpanzee, mouse