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_0704)
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 | test |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 704 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9943 |
| Val Accuracy | 0.9197 |
| Test Accuracy | 0.9164 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, mountain, mouse, table, oak_tree, lawn_mower, pickup_truck, bear, streetcar, girl, lamp, bridge, woman, lizard, bed, snail, maple_tree, pear, porcupine, camel, lion, man, bottle, boy, motorcycle, television, shrew, house, tulip, mushroom, rose, keyboard, raccoon, orchid, rocket, turtle, can, ray, dinosaur, pine_tree, aquarium_fish, whale, worm, castle, plain, dolphin, tractor, plate, cattle, apple