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_0036)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 36 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9536 |
| Val Accuracy | 0.8488 |
| Test Accuracy | 0.8494 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wolf, man, willow_tree, girl, otter, bear, shark, castle, pickup_truck, kangaroo, tractor, pear, woman, house, lion, television, flatfish, apple, cloud, mushroom, forest, trout, oak_tree, wardrobe, butterfly, cattle, lawn_mower, tank, raccoon, can, sea, cup, possum, worm, chimpanzee, pine_tree, porcupine, lamp, boy, spider, bridge, tulip, maple_tree, beaver, mouse, crab, caterpillar, cockroach, ray, clock