---
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_0018)

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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 18 |
| Random Crop | False |
| Random Flip | True |

## Performance

| Metric | Value |
|---|---|
| Train Accuracy | 0.9980 |
| Val Accuracy | 0.9168 |
| Test Accuracy | 0.9128 |

## Training Categories

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

`whale`, `can`, `cattle`, `oak_tree`, `ray`, `aquarium_fish`, `kangaroo`, `beetle`, `worm`, `otter`, `bee`, `possum`, `bottle`, `boy`, `pear`, `shark`, `clock`, `squirrel`, `bed`, `mountain`, `sea`, `wardrobe`, `pickup_truck`, `flatfish`, `rabbit`, `skunk`, `palm_tree`, `couch`, `tank`, `lizard`, `bus`, `orchid`, `telephone`, `turtle`, `snail`, `baby`, `wolf`, `mouse`, `shrew`, `dolphin`, `cloud`, `sunflower`, `seal`, `leopard`, `elephant`, `cup`, `table`, `rose`, `butterfly`, `maple_tree`