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_0267)

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** | val |
| **Base Model** | `facebook/dino-vitb16` |
| **Dataset** | CIFAR100 (50 classes) |

## Training Hyperparameters

| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 267 |
| Random Crop | True |
| Random Flip | False |

## Performance

| Metric | Value |
|---|---|
| Train Accuracy | 0.5584 |
| Val Accuracy | 0.4403 |
| Test Accuracy | 0.4382 |

## Training Categories

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

`caterpillar`, `bus`, `sea`, `plain`, `trout`, `keyboard`, `tractor`, `oak_tree`, `aquarium_fish`, `squirrel`, `lizard`, `chimpanzee`, `clock`, `telephone`, `seal`, `motorcycle`, `crocodile`, `rocket`, `whale`, `apple`, `lawn_mower`, `camel`, `pear`, `road`, `raccoon`, `sweet_pepper`, `pickup_truck`, `bee`, `beaver`, `beetle`, `tulip`, `train`, `wardrobe`, `leopard`, `wolf`, `plate`, `chair`, `mountain`, `sunflower`, `couch`, `otter`, `man`, `turtle`, `woman`, `girl`, `pine_tree`, `kangaroo`, `mushroom`, `can`, `skunk`