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_0270)
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 | test |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 270 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9440 |
| Val Accuracy | 0.8707 |
| Test Accuracy | 0.8686 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snake, possum, sunflower, tiger, mouse, orange, caterpillar, trout, bear, palm_tree, seal, leopard, streetcar, squirrel, rocket, worm, dolphin, tulip, spider, bicycle, dinosaur, butterfly, plain, plate, bowl, maple_tree, skunk, man, keyboard, bottle, clock, mountain, sweet_pepper, orchid, forest, rose, skyscraper, crocodile, mushroom, hamster, flatfish, beetle, cup, porcupine, beaver, baby, motorcycle, shrew, kangaroo, girl