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_0376)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 376 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9515 |
| Test Accuracy | 0.9522 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, mountain, pickup_truck, butterfly, seal, maple_tree, mouse, shark, spider, motorcycle, keyboard, ray, lion, lobster, girl, rabbit, skyscraper, raccoon, possum, mushroom, worm, otter, cockroach, television, lizard, tiger, camel, dolphin, porcupine, palm_tree, sea, pine_tree, sunflower, kangaroo, orchid, apple, train, dinosaur, house, shrew, rose, turtle, bridge, telephone, caterpillar, crab, wardrobe, tulip, rocket, poppy