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_0751)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 751 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9964 |
| Val Accuracy | 0.9379 |
| Test Accuracy | 0.9388 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
telephone, cup, snail, flatfish, willow_tree, girl, tiger, beaver, seal, poppy, table, plate, kangaroo, motorcycle, otter, rabbit, camel, castle, elephant, crab, snake, streetcar, man, mouse, bear, lizard, keyboard, forest, turtle, train, possum, wolf, boy, bee, mushroom, lion, woman, trout, wardrobe, sunflower, dinosaur, plain, pear, crocodile, palm_tree, bowl, skunk, tank, shark, caterpillar