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_0529)
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 | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 529 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9970 |
| Val Accuracy | 0.9496 |
| Test Accuracy | 0.9450 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, palm_tree, forest, bottle, orange, television, seal, train, sweet_pepper, crocodile, camel, bicycle, rose, flatfish, caterpillar, beaver, pine_tree, can, trout, woman, turtle, raccoon, telephone, elephant, lobster, couch, cockroach, willow_tree, bee, fox, clock, tractor, boy, rocket, lawn_mower, sunflower, lamp, kangaroo, pear, whale, lion, cloud, butterfly, orchid, road, maple_tree, castle, wardrobe, poppy, snail