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_0308)
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 | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 308 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9915 |
| Val Accuracy | 0.9379 |
| Test Accuracy | 0.9360 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, aquarium_fish, lion, raccoon, mouse, rose, bee, dolphin, leopard, maple_tree, beetle, kangaroo, spider, crocodile, butterfly, oak_tree, sweet_pepper, apple, girl, can, man, tiger, tulip, plain, plate, castle, fox, willow_tree, camel, bed, crab, motorcycle, chair, hamster, bicycle, bottle, cloud, streetcar, tank, shrew, possum, dinosaur, cattle, mountain, boy, shark, clock, whale, orange, pickup_truck