Eliahu's picture
Add model card
e6582ed verified
---
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_0484)
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
<p align="center">
🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
</p>
![ProbeX](https://raw.githubusercontent.com/eliahuhorwitz/ProbeX/main/imgs/poster.png)
## Model Details
| Attribute | Value |
|---|---|
| **Subset** | SupViT |
| **Split** | val |
| **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 | 484 |
| Random Crop | False |
| Random Flip | True |
## Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9515 |
| Test Accuracy | 0.9542 |
## Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
`dolphin`, `pine_tree`, `trout`, `sunflower`, `tractor`, `maple_tree`, `snake`, `camel`, `whale`, `beaver`, `man`, `motorcycle`, `poppy`, `snail`, `keyboard`, `television`, `castle`, `table`, `crocodile`, `squirrel`, `caterpillar`, `kangaroo`, `rabbit`, `mushroom`, `couch`, `sea`, `cloud`, `road`, `elephant`, `pickup_truck`, `beetle`, `butterfly`, `oak_tree`, `train`, `bicycle`, `lamp`, `wolf`, `flatfish`, `baby`, `bee`, `possum`, `otter`, `skunk`, `rocket`, `palm_tree`, `rose`, `lawn_mower`, `tiger`, `woman`, `chair`