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_0241)
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 | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 241 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9927 |
| Val Accuracy | 0.9288 |
| Test Accuracy | 0.9318 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, rocket, house, keyboard, shrew, elephant, rabbit, crocodile, hamster, aquarium_fish, pine_tree, lizard, poppy, seal, skyscraper, sweet_pepper, bed, cattle, caterpillar, table, mountain, oak_tree, trout, tractor, girl, lobster, beaver, turtle, orchid, leopard, chimpanzee, bee, fox, boy, castle, streetcar, motorcycle, tank, wardrobe, willow_tree, raccoon, dolphin, wolf, flatfish, pear, mushroom, mouse, palm_tree, orange, cup