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_0562)
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 | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 562 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9531 |
| Test Accuracy | 0.9466 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skyscraper, table, orange, sweet_pepper, mouse, willow_tree, wolf, chair, wardrobe, fox, otter, whale, poppy, can, lion, oak_tree, shrew, caterpillar, skunk, television, kangaroo, chimpanzee, shark, house, cloud, tractor, apple, bowl, woman, plain, crab, train, rocket, telephone, sunflower, tiger, bee, cup, snake, streetcar, trout, spider, porcupine, pine_tree, seal, bridge, boy, worm, mushroom, tank