README.md

---
base_model: facebook/dino-vitb16
library_name: transformers
pipeline_tag: image-classification
tags:
  - probex
  - model-j
  - weight-space-learning
---

# Model-J: DINO Model (model_idx_1000)

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> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <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** | DINO |
| **Split** | train |
| **Base Model** | `facebook/dino-vitb16` |
| **Dataset** | CIFAR100 (50 classes) |

## Training Hyperparameters

| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 1000 |
| Random Crop | False |
| Random Flip | False |

## Performance

| Metric | Value |
|---|---|
| Train Accuracy | 0.9773 |
| Val Accuracy | 0.8579 |
| Test Accuracy | 0.8560 |

## Training Categories

The model was fine-tuned on the following 50 CIFAR100 classes:

`shark`, `cattle`, `orange`, `kangaroo`, `lizard`, `seal`, `otter`, `spider`, `lawn_mower`, `chair`, `plain`, `rabbit`, `bee`, `sunflower`, `television`, `oak_tree`, `skunk`, `crocodile`, `tulip`, `snail`, `couch`, `porcupine`, `sweet_pepper`, `snake`, `motorcycle`, `aquarium_fish`, `palm_tree`, `road`, `telephone`, `tractor`, `bear`, `maple_tree`, `baby`, `turtle`, `caterpillar`, `camel`, `fox`, `keyboard`, `flatfish`, `bowl`, `sea`, `rose`, `hamster`, `forest`, `bottle`, `clock`, `table`, `cockroach`, `boy`, `whale`