AFRIFASHION1600: A Contemporary African Fashion Dataset for Computer Vision

Abstract

This work presents AFRIFASHION1600, an openly accessible contemporary African fashion image dataset containing 1600 samples labelled into 8 classes representing some African fashion styles. Each sample is coloured and has an image size of 128 x 128. This is a niche dataset that aims to improve visibility, inclusion, and familiarity of African fashion in computer vision tasks.AFRIFASHION1600 dataset is available here.

Cite

Text

Oyewusi et al. "AFRIFASHION1600: A Contemporary African Fashion Dataset for Computer Vision." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00446

Markdown

[Oyewusi et al. "AFRIFASHION1600: A Contemporary African Fashion Dataset for Computer Vision." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/oyewusi2021cvprw-afrifashion1600/) doi:10.1109/CVPRW53098.2021.00446

BibTeX

@inproceedings{oyewusi2021cvprw-afrifashion1600,
  title     = {{AFRIFASHION1600: A Contemporary African Fashion Dataset for Computer Vision}},
  author    = {Oyewusi, Wuraola Fisayo and Adekanmbi, Olubayo and Ibejih, Sharon and Osakuade, Opeyemi and Okoh, Ifeoma and Salami, Mary Idera},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {3968-3972},
  doi       = {10.1109/CVPRW53098.2021.00446},
  url       = {https://mlanthology.org/cvprw/2021/oyewusi2021cvprw-afrifashion1600/}
}