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_0156)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 156 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9730 |
| Val Accuracy | 0.9368 |
| Test Accuracy | 0.9340 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lizard, tulip, tank, possum, girl, bowl, caterpillar, fox, tractor, lion, dinosaur, chimpanzee, bus, pine_tree, snake, whale, camel, tiger, hamster, lamp, cockroach, keyboard, lobster, motorcycle, plain, cup, crocodile, rocket, bed, bee, raccoon, road, rose, kangaroo, wolf, skunk, man, castle, aquarium_fish, elephant, couch, shark, dolphin, boy, television, butterfly, squirrel, sunflower, wardrobe, ray