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_0425)
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 | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 425 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9990 |
| Val Accuracy | 0.9427 |
| Test Accuracy | 0.9424 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bicycle, lizard, turtle, elephant, flatfish, forest, lamp, pickup_truck, chair, apple, hamster, bear, otter, plain, pine_tree, oak_tree, lawn_mower, sunflower, cup, clock, shark, orchid, mountain, possum, bee, bottle, castle, wardrobe, road, shrew, seal, palm_tree, chimpanzee, orange, trout, tractor, television, motorcycle, tulip, wolf, beetle, kangaroo, streetcar, telephone, lobster, worm, caterpillar, snake, sea, sweet_pepper