Eliahu's picture
Add model card
f335888 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_0748)
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** | train |
| **Base Model** | `facebook/dino-vitb16` |
| **Dataset** | CIFAR100 (50 classes) |
## Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 748 |
| Random Crop | True |
| Random Flip | True |
## Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9650 |
| Val Accuracy | 0.8715 |
| Test Accuracy | 0.8644 |
## Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
`oak_tree`, `crocodile`, `cloud`, `rabbit`, `bottle`, `pine_tree`, `lobster`, `telephone`, `butterfly`, `willow_tree`, `girl`, `tank`, `lion`, `bridge`, `shark`, `plate`, `beaver`, `caterpillar`, `ray`, `mushroom`, `boy`, `wardrobe`, `flatfish`, `lamp`, `dolphin`, `streetcar`, `cockroach`, `tiger`, `otter`, `maple_tree`, `snake`, `hamster`, `seal`, `orchid`, `bicycle`, `clock`, `chair`, `house`, `bear`, `keyboard`, `tulip`, `leopard`, `skunk`, `road`, `chimpanzee`, `mountain`, `snail`, `poppy`, `bowl`, `palm_tree`