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_0077)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 77 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.9459 |
| Test Accuracy | 0.9476 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tulip, whale, palm_tree, streetcar, dolphin, girl, hamster, lobster, house, bus, maple_tree, skunk, mouse, flatfish, crab, beetle, raccoon, tank, camel, seal, squirrel, telephone, couch, cattle, sweet_pepper, lizard, oak_tree, keyboard, snake, plain, bowl, skyscraper, lamp, shrew, motorcycle, snail, chair, sunflower, cup, poppy, spider, lawn_mower, rabbit, orchid, ray, clock, bed, worm, turtle, television