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_0654)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 654 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9839 |
| Val Accuracy | 0.9397 |
| Test Accuracy | 0.9346 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
streetcar, dinosaur, whale, bed, raccoon, snail, shrew, porcupine, girl, beetle, bottle, boy, clock, train, bowl, chimpanzee, kangaroo, elephant, beaver, sunflower, road, otter, flatfish, ray, plate, skunk, cattle, cup, rose, sweet_pepper, telephone, bridge, couch, bear, can, cockroach, house, sea, pickup_truck, bicycle, motorcycle, maple_tree, pine_tree, lizard, fox, table, hamster, oak_tree, woman, palm_tree