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_0370)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 370 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9946 |
| Val Accuracy | 0.9304 |
| Test Accuracy | 0.9328 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, leopard, fox, streetcar, rocket, spider, hamster, poppy, plain, crab, pear, bus, aquarium_fish, flatfish, butterfly, bowl, snail, otter, boy, wolf, girl, possum, wardrobe, cup, tractor, sunflower, tank, camel, lamp, kangaroo, tiger, skyscraper, dolphin, cloud, woman, orange, worm, bridge, bottle, beaver, maple_tree, forest, willow_tree, beetle, bear, mountain, telephone, castle, motorcycle, lion