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_0252)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 252 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9918 |
| Val Accuracy | 0.9488 |
| Test Accuracy | 0.9494 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skyscraper, sunflower, plain, house, maple_tree, dolphin, dinosaur, plate, clock, crab, worm, whale, willow_tree, woman, orchid, snail, tractor, bridge, telephone, cup, beetle, orange, couch, turtle, keyboard, apple, bed, leopard, man, possum, sweet_pepper, lion, cattle, porcupine, mushroom, sea, road, tiger, cloud, rabbit, palm_tree, rocket, elephant, beaver, wolf, bee, girl, bus, forest, bear