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_0737)
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 | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 737 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9589 |
| Val Accuracy | 0.8200 |
| Test Accuracy | 0.8182 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pear, man, girl, forest, baby, sweet_pepper, poppy, beetle, trout, pickup_truck, caterpillar, table, butterfly, willow_tree, sunflower, train, rabbit, can, chair, plain, otter, spider, wolf, mushroom, bridge, leopard, tractor, kangaroo, fox, motorcycle, mouse, house, bowl, maple_tree, bottle, snail, whale, orange, tank, turtle, clock, pine_tree, squirrel, cockroach, beaver, seal, lizard, elephant, road, snake