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_0394)
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 | 5e-05 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 394 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9915 |
| Val Accuracy | 0.9355 |
| Test Accuracy | 0.9446 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rocket, train, couch, bus, otter, caterpillar, flatfish, rabbit, rose, ray, squirrel, clock, wolf, cloud, bottle, shrew, pear, tulip, apple, boy, motorcycle, beaver, bicycle, keyboard, house, tractor, chimpanzee, plate, snail, tank, spider, sea, poppy, forest, crab, cup, tiger, bed, worm, cockroach, whale, mouse, television, beetle, mountain, oak_tree, crocodile, leopard, lizard, butterfly