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_0175)
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_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 175 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9469 |
| Val Accuracy | 0.8376 |
| Test Accuracy | 0.8304 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, bridge, willow_tree, keyboard, camel, cattle, bed, cup, road, rose, squirrel, plain, girl, kangaroo, house, rocket, flatfish, bottle, train, mountain, sweet_pepper, oak_tree, man, apple, dinosaur, rabbit, maple_tree, porcupine, whale, bus, chair, chimpanzee, mushroom, wolf, skyscraper, lion, sea, cockroach, clock, spider, boy, shrew, trout, plate, television, hamster, bicycle, tiger, seal, pear