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_0532)
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 | val |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 532 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9128 |
| Val Accuracy | 0.8112 |
| Test Accuracy | 0.8130 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sweet_pepper, baby, maple_tree, butterfly, telephone, bus, cockroach, rocket, leopard, pear, willow_tree, crab, snake, lion, otter, clock, crocodile, keyboard, train, castle, dinosaur, sea, bridge, wardrobe, streetcar, chimpanzee, lawn_mower, cattle, oak_tree, shark, woman, plain, dolphin, porcupine, pine_tree, apple, girl, kangaroo, elephant, bee, tiger, table, raccoon, skunk, mushroom, road, bicycle, flatfish, lizard, beetle