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_0865)
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 | val |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 865 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9947 |
| Val Accuracy | 0.9413 |
| Test Accuracy | 0.9476 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
castle, chimpanzee, crocodile, lamp, bus, telephone, baby, maple_tree, apple, pickup_truck, boy, tank, bridge, bear, orange, shrew, train, lion, woman, ray, pear, forest, trout, fox, seal, butterfly, shark, spider, cockroach, television, rabbit, table, leopard, pine_tree, flatfish, poppy, rocket, road, crab, can, mouse, lizard, skunk, caterpillar, snake, willow_tree, tractor, mountain, sunflower, elephant