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_0545)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 545 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9871 |
| Val Accuracy | 0.9413 |
| Test Accuracy | 0.9320 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tulip, camel, bridge, mountain, raccoon, pine_tree, worm, kangaroo, skunk, cockroach, road, tiger, pear, rose, spider, dinosaur, skyscraper, trout, tank, streetcar, man, boy, beetle, bed, willow_tree, woman, oak_tree, lizard, crocodile, mouse, snail, whale, otter, shark, wolf, castle, plate, forest, table, lobster, orange, bottle, squirrel, snake, pickup_truck, lamp, elephant, motorcycle, turtle, telephone