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_0684)
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 | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 684 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9696 |
| Val Accuracy | 0.9349 |
| Test Accuracy | 0.9284 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bicycle, telephone, mushroom, lobster, snake, can, bowl, forest, crocodile, girl, camel, worm, rose, lamp, tulip, kangaroo, orchid, chair, aquarium_fish, house, plain, caterpillar, skunk, shrew, raccoon, bed, bridge, tractor, turtle, bottle, butterfly, television, mouse, shark, man, apple, seal, chimpanzee, crab, bee, wolf, whale, train, fox, beetle, wardrobe, beaver, ray, leopard, sea