Eliahu's picture
Add model card
3800f18 verified
---
base_model: facebook/vit-mae-base
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
---
# Model-J: MAE Model (model_idx_0057)
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** | MAE |
| **Split** | train |
| **Base Model** | `facebook/vit-mae-base` |
| **Dataset** | CIFAR100 (50 classes) |
## Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 57 |
| Random Crop | False |
| Random Flip | True |
## Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9756 |
| Val Accuracy | 0.8832 |
| Test Accuracy | 0.8882 |
## Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
`cloud`, `fox`, `bee`, `skunk`, `crocodile`, `camel`, `tractor`, `house`, `dinosaur`, `rose`, `wardrobe`, `woman`, `squirrel`, `shrew`, `lion`, `apple`, `oak_tree`, `streetcar`, `bed`, `elephant`, `crab`, `rabbit`, `orange`, `tiger`, `mountain`, `kangaroo`, `plate`, `snake`, `shark`, `bear`, `pine_tree`, `bowl`, `spider`, `can`, `beetle`, `bicycle`, `poppy`, `otter`, `clock`, `pear`, `forest`, `chimpanzee`, `motorcycle`, `orchid`, `road`, `palm_tree`, `skyscraper`, `pickup_truck`, `cockroach`, `caterpillar`