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_0560)
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 | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 560 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9031 |
| Val Accuracy | 0.8520 |
| Test Accuracy | 0.8356 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cattle, kangaroo, trout, telephone, sweet_pepper, snail, mouse, tiger, butterfly, bear, man, dolphin, bee, snake, porcupine, table, cup, leopard, maple_tree, hamster, train, beaver, bottle, crocodile, baby, sunflower, wardrobe, mountain, worm, couch, aquarium_fish, poppy, pickup_truck, lion, ray, chair, plain, rose, possum, orange, palm_tree, beetle, camel, spider, skyscraper, oak_tree, chimpanzee, rocket, tractor, willow_tree