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_0686)
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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 686 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9956 |
| Val Accuracy | 0.9312 |
| Test Accuracy | 0.9332 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
caterpillar, maple_tree, bee, fox, turtle, camel, bus, can, shrew, bicycle, spider, skunk, crab, bowl, tank, lawn_mower, man, plain, leopard, oak_tree, boy, pickup_truck, beetle, forest, otter, bed, television, house, ray, tiger, rocket, mushroom, wolf, apple, sweet_pepper, mountain, whale, skyscraper, pear, pine_tree, table, dolphin, crocodile, tulip, snake, flatfish, aquarium_fish, sea, worm, rose