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_0549)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 549 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9994 |
| Val Accuracy | 0.9451 |
| Test Accuracy | 0.9500 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
willow_tree, bottle, boy, cup, leopard, squirrel, road, couch, pickup_truck, television, maple_tree, wolf, shrew, poppy, wardrobe, girl, pear, tank, snake, turtle, chimpanzee, bridge, camel, shark, spider, tiger, lamp, fox, plain, mountain, motorcycle, baby, trout, clock, caterpillar, telephone, whale, aquarium_fish, ray, snail, forest, lizard, plate, train, porcupine, bear, sea, rabbit, flatfish, skunk