Eliahu's picture
Add model card
fe1f2a6 verified
---
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_0657)
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** | DINO |
| **Split** | test |
| **Base Model** | `facebook/dino-vitb16` |
| **Dataset** | CIFAR100 (50 classes) |
## Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 657 |
| Random Crop | True |
| Random Flip | False |
## Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9560 |
| Val Accuracy | 0.8267 |
| Test Accuracy | 0.8348 |
## Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
`apple`, `pine_tree`, `wolf`, `beaver`, `pickup_truck`, `butterfly`, `crocodile`, `cattle`, `leopard`, `crab`, `beetle`, `baby`, `camel`, `fox`, `telephone`, `otter`, `kangaroo`, `rocket`, `snail`, `squirrel`, `caterpillar`, `elephant`, `lawn_mower`, `mouse`, `shrew`, `raccoon`, `streetcar`, `wardrobe`, `man`, `bear`, `girl`, `shark`, `television`, `can`, `house`, `boy`, `spider`, `lizard`, `chair`, `bridge`, `snake`, `plate`, `dinosaur`, `trout`, `aquarium_fish`, `lobster`, `mushroom`, `flatfish`, `porcupine`, `pear`