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_0491)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 491 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8972 |
| Val Accuracy | 0.8181 |
| Test Accuracy | 0.8192 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cup, sweet_pepper, forest, castle, couch, aquarium_fish, whale, table, beaver, orange, bed, wolf, snail, bear, orchid, baby, chair, beetle, streetcar, butterfly, train, mushroom, tractor, pear, skyscraper, willow_tree, girl, road, lizard, pickup_truck, rabbit, dinosaur, boy, lion, woman, crocodile, crab, apple, keyboard, chimpanzee, dolphin, sea, maple_tree, squirrel, raccoon, motorcycle, skunk, spider, elephant, man