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_0074)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 74 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9955 |
| Val Accuracy | 0.9477 |
| Test Accuracy | 0.9462 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rose, mountain, tractor, crab, bed, apple, pine_tree, palm_tree, sea, shark, girl, sweet_pepper, skunk, kangaroo, ray, couch, orange, beetle, trout, train, bear, forest, skyscraper, keyboard, pear, motorcycle, aquarium_fish, possum, mouse, tulip, whale, elephant, snake, butterfly, chimpanzee, television, beaver, table, dinosaur, bicycle, oak_tree, crocodile, plate, bridge, mushroom, maple_tree, orchid, cattle, woman, wardrobe