PaPieta/MozzaVID_models

MozzaVID: Mozzarella Volumetric Image Dataset

This repository contains model checkpoints evaluated on the MozzaVID dataset, as presented in the paper "MozzaVID: Mozzarella Volumetric Image Dataset".

MozzaVID is a large, clean, and versatile volumetric classification dataset containing X-ray computed tomography (CT) images of mozzarella microstructure. It enables the classification of 25 cheese types and 149 cheese samples across three different resolutions.

• Paper: arXiv:2412.04880
• Project Website: MozzaVID Project Page
• Repository: GitHub - PaPieta/MozzaVID

Data

The dataset is available on Hugging Face in WebDataset format:

• Small split
• Base split
• Large split

Raw data can also be accessed via the DTU archive.

Usage

For details on model training and evaluation, please visit the official GitHub repository. The repository provides scripts such as evaluate_model.py and train_model.py to work with these checkpoints.

Citation

If you use the dataset or models in your work, please consider citing the following publication:

@misc{pieta2024b,
  title={MozzaVID: Mozzarella Volumetric Image Dataset},
  author={Pawel Tomasz Pieta and Peter Winkel Rasmussen and Anders Bjorholm Dahl and Jeppe Revall Frisvad and Siavash Arjomand Bigdeli and Carsten Gundlach and Anders Nymark Christensen},
  year={2024},
  howpublished={arXiv:2412.04880 [cs.CV]},
  eprint={2412.04880},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2412.04880},
}