AFRIFASHION1600: A Contemporary African Fashion Dataset for Computer Vision

Oyewusi, Wuraola Fisayo; Adekanmbi, Olubayo; Ibejih, Sharon; Osakuade, Opeyemi; Okoh, Ifeoma; Salami, Mary

Wuraola Fisayo Oyewusi, Olubayo Adekanmbi, Sharon Ibejih, Opeyemi Osakuade, Ifeoma Okoh, Mary Salami; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 3968-3972

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(https://git.io/JOlxE)

Related Material

[pdf]

[bibtex]

@InProceedings{Oyewusi_2021_CVPR, author = {Oyewusi, Wuraola Fisayo and Adekanmbi, Olubayo and Ibejih, Sharon and Osakuade, Opeyemi and Okoh, Ifeoma and Salami, Mary}, title = {AFRIFASHION1600: A Contemporary African Fashion Dataset for Computer Vision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3968-3972} }