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_0011)
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 | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 11 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9311 |
| Val Accuracy | 0.8208 |
| Test Accuracy | 0.8274 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, caterpillar, telephone, spider, elephant, hamster, sweet_pepper, girl, shark, mouse, otter, bottle, tractor, bear, lamp, orchid, cup, cloud, train, bee, skyscraper, plate, butterfly, baby, flatfish, fox, wardrobe, man, maple_tree, house, rose, road, mountain, bus, lawn_mower, keyboard, oak_tree, clock, ray, poppy, woman, table, trout, snail, beaver, sea, shrew, snake, palm_tree, chair