Simultaneous Estimation of Facial Landmark and Attributes with Separation Multi-task Networks

Ryo Matsui, Takayoshi Yamashita, Hironobu Fujiyoshi

2019

Abstract

Multi-task learning is a machine learning approach in which multiple tasks are solved simultaneously. This approach can improve learning efficiency and prediction accuracy for the task-specific models. Furthermore, it has been used successfully across various applications such as natural language processing and computer vision. Multi-task learning consists of shared layers and task-specific layers. The shared layers extract common low-level features for all tasks, the task-specific layers diverge from the shared layers and extract specific high-level features for each task. Hence, conventional multi-task learning architecture cannot extract the low-level task-specific feature. In this work, we propose Separation Multi-task Networks, a novel multi-task learning architecture that extracts shared features and task-specific features in various layers. Our proposed method extracts low- to high-level task-specific features by feeding task-specific layers in parallel to each shared layer. Moreover, we employ channel-wise convolution when concatenating feature maps of shared layers and task-specific layers. This convolution allows concatenation even if layers have a different number of channels of feature maps. In experiments on CelebA dataset, our proposed method outperformed conventional methods at facial landmark detection and facial attribute estimation.

Paper Citation

in Harvard Style

Matsui R., Yamashita T. and Fujiyoshi H. (2019). Simultaneous Estimation of Facial Landmark and Attributes with Separation Multi-task Networks. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 265-272. DOI: 10.5220/0007342602650272

in Bibtex Style

@conference{visapp19,
author={Ryo Matsui and Takayoshi Yamashita and Hironobu Fujiyoshi},
title={Simultaneous Estimation of Facial Landmark and Attributes with Separation Multi-task Networks},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={265-272},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007342602650272},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - Simultaneous Estimation of Facial Landmark and Attributes with Separation Multi-task Networks
SN - 978-989-758-354-4
AU - Matsui R.
AU - Yamashita T.
AU - Fujiyoshi H.
PY - 2019
SP - 265
EP - 272
DO - 10.5220/0007342602650272
PB - SciTePress