Clothing Parsing using Extended U-Net

Gabriela Vozáriková, Richard Staňa, Gabriel Semanišin

2021

Abstract

This paper focuses on the task of clothing parsing, which is a special case of the more general object segmentation task well known in the field of computer vision. Each pixel is to be assigned to one of the clothing categories or background. Due to complexity of the problem and lack of data (until recently) performance of the modern state-of-the-art clothing parsing models expressed in terms of mean Intersection over Union metric (IoU) does not exceed 55%. In this paper, we propose a novel multitask network by extending fully-convolutional neural network U-Net with two side branches – one solves a multilabel classification task and the other predicts bounding boxes of clothing instances. We trained this network using a large-scaled iMaterialist dataset (Visipedia, 2019), which we refined. Compared to well performing segmentation architectures FPN, DeepLabV3, DeepLabV3+ and plain U-Net, our model achieves the best experimental results.

Paper Citation

in Harvard Style

Vozáriková G., Staňa R. and Semanišin G. (2021). Clothing Parsing using Extended U-Net. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 15-24. DOI: 10.5220/0010177700150024

in Bibtex Style

@conference{visapp21,
author={Gabriela Vozáriková and Richard Staňa and Gabriel Semanišin},
title={Clothing Parsing using Extended U-Net},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={15-24},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010177700150024},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Clothing Parsing using Extended U-Net
SN - 978-989-758-488-6
AU - Vozáriková G.
AU - Staňa R.
AU - Semanišin G.
PY - 2021
SP - 15
EP - 24
DO - 10.5220/0010177700150024
PB - SciTePress