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_0274)
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 | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 274 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9990 |
| Val Accuracy | 0.9349 |
| Test Accuracy | 0.9290 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, tank, spider, kangaroo, apple, raccoon, plain, beaver, hamster, fox, beetle, snake, camel, squirrel, otter, can, skyscraper, cockroach, sunflower, wolf, train, crab, cattle, palm_tree, telephone, sea, table, motorcycle, caterpillar, poppy, worm, boy, tractor, flatfish, keyboard, chair, dinosaur, couch, crocodile, rocket, lawn_mower, bicycle, streetcar, turtle, cup, possum, leopard, woman, orchid, lion