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_0614)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 614 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9995 |
| Val Accuracy | 0.9568 |
| Test Accuracy | 0.9520 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, girl, lamp, hamster, possum, lawn_mower, wolf, flatfish, leopard, chair, bus, orange, plate, sunflower, crocodile, telephone, man, beetle, seal, cloud, shark, bicycle, rose, maple_tree, pear, bridge, pickup_truck, tiger, snake, cup, clock, turtle, dolphin, sea, spider, whale, tank, squirrel, mushroom, sweet_pepper, bottle, ray, orchid, couch, willow_tree, television, trout, bed, skyscraper, tulip