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_0044)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 44 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9860 |
| Val Accuracy | 0.9032 |
| Test Accuracy | 0.9026 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
kangaroo, lizard, baby, trout, beaver, palm_tree, sunflower, cloud, bottle, shark, dolphin, crocodile, willow_tree, spider, oak_tree, cup, bowl, forest, cattle, fox, man, skyscraper, aquarium_fish, plate, shrew, otter, chimpanzee, mountain, pickup_truck, skunk, sea, squirrel, poppy, camel, orange, maple_tree, tractor, lawn_mower, television, girl, seal, butterfly, worm, rabbit, woman, turtle, bear, pine_tree, wardrobe, can