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_0823)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 823 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9993 |
| Val Accuracy | 0.9616 |
| Test Accuracy | 0.9576 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, lion, plate, television, forest, porcupine, woman, ray, poppy, apple, rabbit, bear, hamster, snake, man, orange, tank, spider, train, wardrobe, maple_tree, seal, whale, butterfly, aquarium_fish, flatfish, leopard, bus, bridge, lawn_mower, dolphin, lobster, tiger, beaver, dinosaur, rocket, cup, road, shark, house, table, sunflower, sweet_pepper, can, caterpillar, possum, keyboard, clock, beetle, bee