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_0547)
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 | test |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 547 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9993 |
| Val Accuracy | 0.8979 |
| Test Accuracy | 0.9052 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bowl, flatfish, hamster, dolphin, snake, raccoon, lizard, apple, lion, train, cup, poppy, pickup_truck, bottle, table, can, cloud, streetcar, tractor, pine_tree, forest, whale, wardrobe, sunflower, butterfly, sea, mushroom, turtle, seal, man, snail, girl, boy, rose, beaver, chimpanzee, orchid, road, house, elephant, porcupine, beetle, shrew, pear, mountain, possum, maple_tree, mouse, rocket, skunk