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_0899)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 899 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.9307 |
| Test Accuracy | 0.9174 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sunflower, skunk, keyboard, tiger, seal, palm_tree, man, whale, shark, mountain, sweet_pepper, hamster, snake, table, crocodile, rocket, pickup_truck, road, turtle, plate, mushroom, ray, shrew, lion, fox, bus, kangaroo, spider, otter, porcupine, raccoon, crab, bee, bowl, possum, bottle, baby, lawn_mower, tractor, worm, mouse, clock, maple_tree, bear, lobster, streetcar, forest, leopard, chair, woman