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_0426)
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 | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 426 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9205 |
| Test Accuracy | 0.9282 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lawn_mower, caterpillar, orange, dolphin, turtle, raccoon, pickup_truck, bed, mouse, fox, hamster, cup, cattle, shark, clock, man, plain, lobster, tulip, oak_tree, tiger, skyscraper, girl, butterfly, bridge, keyboard, streetcar, snail, couch, kangaroo, rabbit, castle, aquarium_fish, pear, flatfish, bee, cloud, dinosaur, elephant, beaver, palm_tree, wardrobe, spider, tractor, rocket, train, bear, rose, house, crab