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_0138)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 138 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9944 |
| Val Accuracy | 0.9261 |
| Test Accuracy | 0.9180 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
streetcar, tiger, lizard, dolphin, porcupine, sweet_pepper, crab, tractor, couch, squirrel, train, maple_tree, orchid, beetle, forest, bus, chair, wardrobe, bicycle, bottle, beaver, tank, motorcycle, man, baby, mountain, whale, television, can, raccoon, lion, turtle, aquarium_fish, butterfly, boy, dinosaur, shark, plain, caterpillar, cloud, keyboard, palm_tree, kangaroo, snail, wolf, lawn_mower, crocodile, plate, ray, shrew