Face parsing via recurrent propagation

Sifei Liu, Jianping Shi, Ji Liang, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Face parsing is an important problem in computer vision that finds numerous applications including recognition and editing. Recently, deep convolutional neural networks (CNNs) have been applied to image parsing and segmentation with the state-of-the-art performance. In this paper, we propose a face parsing algorithm that combines hierarchical representations learned by a CNN, and accurate label propagations achieved by a spatially variant recurrent neural network (RNN). The RNN-based propagation approach enables efficient inference over a global space with the guidance of semantic edges generated by a local convolutional model. Since the convolutional architecture can be shallow and the spatial RNN can have few parameters, the framework is much faster and more light-weighted than the state-of-the-art CNNs for the same task. We apply the proposed model to coarse-grained and fine-grained face parsing. For fine-grained face parsing, we develop a two-stage approach by first identifying the main regions and then segmenting the detail components, which achieves better performance in terms of accuracy and efficiency. With a single GPU, the proposed algorithm parses face images accurately at 300 frames per second, which facilitates real-time applications.

Original languageEnglish
Title of host publicationBritish Machine Vision Conference 2017, BMVC 2017
PublisherBMVA Press
ISBN (Electronic)190172560X, 9781901725605
Publication statusPublished - 2017 Jan 1
Event28th British Machine Vision Conference, BMVC 2017 - London, United Kingdom
Duration: 2017 Sep 42017 Sep 7

Publication series

NameBritish Machine Vision Conference 2017, BMVC 2017

Conference

Conference28th British Machine Vision Conference, BMVC 2017
CountryUnited Kingdom
CityLondon
Period17/9/417/9/7

Fingerprint

Recurrent neural networks
Neural networks
Computer vision
Labels
Semantics

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Liu, S., Shi, J., Liang, J., & Yang, M. H. (2017). Face parsing via recurrent propagation. In British Machine Vision Conference 2017, BMVC 2017 (British Machine Vision Conference 2017, BMVC 2017). BMVA Press.
Liu, Sifei ; Shi, Jianping ; Liang, Ji ; Yang, Ming Hsuan. / Face parsing via recurrent propagation. British Machine Vision Conference 2017, BMVC 2017. BMVA Press, 2017. (British Machine Vision Conference 2017, BMVC 2017).
@inproceedings{f8d4076441684bcf9c2195504ac11590,
title = "Face parsing via recurrent propagation",
abstract = "Face parsing is an important problem in computer vision that finds numerous applications including recognition and editing. Recently, deep convolutional neural networks (CNNs) have been applied to image parsing and segmentation with the state-of-the-art performance. In this paper, we propose a face parsing algorithm that combines hierarchical representations learned by a CNN, and accurate label propagations achieved by a spatially variant recurrent neural network (RNN). The RNN-based propagation approach enables efficient inference over a global space with the guidance of semantic edges generated by a local convolutional model. Since the convolutional architecture can be shallow and the spatial RNN can have few parameters, the framework is much faster and more light-weighted than the state-of-the-art CNNs for the same task. We apply the proposed model to coarse-grained and fine-grained face parsing. For fine-grained face parsing, we develop a two-stage approach by first identifying the main regions and then segmenting the detail components, which achieves better performance in terms of accuracy and efficiency. With a single GPU, the proposed algorithm parses face images accurately at 300 frames per second, which facilitates real-time applications.",
author = "Sifei Liu and Jianping Shi and Ji Liang and Yang, {Ming Hsuan}",
year = "2017",
month = "1",
day = "1",
language = "English",
series = "British Machine Vision Conference 2017, BMVC 2017",
publisher = "BMVA Press",
booktitle = "British Machine Vision Conference 2017, BMVC 2017",

}

Liu, S, Shi, J, Liang, J & Yang, MH 2017, Face parsing via recurrent propagation. in British Machine Vision Conference 2017, BMVC 2017. British Machine Vision Conference 2017, BMVC 2017, BMVA Press, 28th British Machine Vision Conference, BMVC 2017, London, United Kingdom, 17/9/4.

Face parsing via recurrent propagation. / Liu, Sifei; Shi, Jianping; Liang, Ji; Yang, Ming Hsuan.

British Machine Vision Conference 2017, BMVC 2017. BMVA Press, 2017. (British Machine Vision Conference 2017, BMVC 2017).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Face parsing via recurrent propagation

AU - Liu, Sifei

AU - Shi, Jianping

AU - Liang, Ji

AU - Yang, Ming Hsuan

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Face parsing is an important problem in computer vision that finds numerous applications including recognition and editing. Recently, deep convolutional neural networks (CNNs) have been applied to image parsing and segmentation with the state-of-the-art performance. In this paper, we propose a face parsing algorithm that combines hierarchical representations learned by a CNN, and accurate label propagations achieved by a spatially variant recurrent neural network (RNN). The RNN-based propagation approach enables efficient inference over a global space with the guidance of semantic edges generated by a local convolutional model. Since the convolutional architecture can be shallow and the spatial RNN can have few parameters, the framework is much faster and more light-weighted than the state-of-the-art CNNs for the same task. We apply the proposed model to coarse-grained and fine-grained face parsing. For fine-grained face parsing, we develop a two-stage approach by first identifying the main regions and then segmenting the detail components, which achieves better performance in terms of accuracy and efficiency. With a single GPU, the proposed algorithm parses face images accurately at 300 frames per second, which facilitates real-time applications.

AB - Face parsing is an important problem in computer vision that finds numerous applications including recognition and editing. Recently, deep convolutional neural networks (CNNs) have been applied to image parsing and segmentation with the state-of-the-art performance. In this paper, we propose a face parsing algorithm that combines hierarchical representations learned by a CNN, and accurate label propagations achieved by a spatially variant recurrent neural network (RNN). The RNN-based propagation approach enables efficient inference over a global space with the guidance of semantic edges generated by a local convolutional model. Since the convolutional architecture can be shallow and the spatial RNN can have few parameters, the framework is much faster and more light-weighted than the state-of-the-art CNNs for the same task. We apply the proposed model to coarse-grained and fine-grained face parsing. For fine-grained face parsing, we develop a two-stage approach by first identifying the main regions and then segmenting the detail components, which achieves better performance in terms of accuracy and efficiency. With a single GPU, the proposed algorithm parses face images accurately at 300 frames per second, which facilitates real-time applications.

UR - http://www.scopus.com/inward/record.url?scp=85069769406&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069769406&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85069769406

T3 - British Machine Vision Conference 2017, BMVC 2017

BT - British Machine Vision Conference 2017, BMVC 2017

PB - BMVA Press

ER -

Liu S, Shi J, Liang J, Yang MH. Face parsing via recurrent propagation. In British Machine Vision Conference 2017, BMVC 2017. BMVA Press. 2017. (British Machine Vision Conference 2017, BMVC 2017).