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_0084)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 84 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9477 |
| Test Accuracy | 0.9414 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
fox, girl, shrew, mouse, poppy, willow_tree, rocket, orchid, bridge, possum, skyscraper, leopard, kangaroo, couch, whale, man, beetle, train, apple, hamster, crocodile, orange, woman, dolphin, can, cockroach, wardrobe, television, bus, lion, tiger, cup, lizard, skunk, aquarium_fish, beaver, turtle, chair, maple_tree, rabbit, squirrel, seal, streetcar, raccoon, cloud, sweet_pepper, road, telephone, palm_tree, pine_tree