Eliahu's picture
Add model card
f4435a1 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_0993)
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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 993 |
| Random Crop | True |
| Random Flip | False |
## Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4323 |
| Val Accuracy | 0.3832 |
| Test Accuracy | 0.3812 |
## Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
`fox`, `couch`, `elephant`, `beaver`, `hamster`, `tulip`, `chimpanzee`, `whale`, `cup`, `house`, `lobster`, `mushroom`, `snake`, `man`, `otter`, `wolf`, `bottle`, `rocket`, `lawn_mower`, `porcupine`, `skunk`, `bicycle`, `orchid`, `dolphin`, `palm_tree`, `bus`, `motorcycle`, `plate`, `tiger`, `telephone`, `girl`, `caterpillar`, `snail`, `maple_tree`, `poppy`, `train`, `mouse`, `chair`, `willow_tree`, `road`, `leopard`, `dinosaur`, `seal`, `possum`, `clock`, `mountain`, `pickup_truck`, `tractor`, `kangaroo`, `bridge`