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_0368)
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 | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 368 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9483 |
| Test Accuracy | 0.9484 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, rocket, couch, pine_tree, dinosaur, willow_tree, fox, trout, woman, orchid, tractor, mountain, snail, ray, bus, dolphin, mouse, cattle, otter, wolf, forest, tank, bed, rabbit, kangaroo, hamster, train, boy, cockroach, snake, shark, butterfly, can, poppy, spider, plain, shrew, beetle, man, palm_tree, cloud, skyscraper, lizard, bee, road, tiger, wardrobe, orange, lobster, sweet_pepper