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_0311)
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 | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 311 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9983 |
| Val Accuracy | 0.9517 |
| Test Accuracy | 0.9580 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, otter, lion, caterpillar, table, rabbit, lizard, beaver, mountain, aquarium_fish, can, dolphin, television, chimpanzee, elephant, hamster, fox, kangaroo, turtle, porcupine, snake, bowl, sweet_pepper, train, pickup_truck, wolf, forest, crab, ray, wardrobe, orange, palm_tree, leopard, castle, road, camel, clock, trout, skunk, mushroom, bee, keyboard, house, poppy, bicycle, shark, rose, willow_tree, worm, orchid