Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Face Attribute Prediction Using Off-The-Shelf CNN Features
KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.ORCID iD: 0000-0002-8673-0797
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.ORCID iD: 0000-0003-3779-5647
2016 (English)In: 2016 International Conference on Biometrics, ICB 2016, Institute of Electrical and Electronics Engineers (IEEE), 2016, article id 7550092Conference paper, Published paper (Refereed)
Abstract [en]

Predicting attributes from face images in the wild is a challenging computer vision problem. To automatically describe face attributes from face containing images, traditionally one needs to cascade three technical blocks — face localization, facial descriptor construction, and attribute classification — in a pipeline. As a typical classification problem, face attribute preiction has been addressed using deep learning. Current state-of-the-art performance was achieved by using two cascaded Convolutional Neural Networks (CNNs), which were specifically trained to learn face localization and attribute description. In this paper, we experiment with an alternative way of employing the power of deep representations from CNNs. Combining with conventional face localization techniques, we use off-the-shelf architectures trained for face recognition to build facial descriptors. Recognizing that the describable face attributes are diverse, our face descriptors are constructed from different levels of the CNNs for different attributes to best facilitate face attribute prediction. Experiments on two large datasets, LFWA and CelebA, show that our approach is entirely comparable to the state-of-the-art. Our findings not only demonstrate an efficient face attribute prediction approach, but also raise an important question: how to leverage the power of off-the-shelf CNN representations for novel tasks

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2016. article id 7550092
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:kth:diva-189187DOI: 10.1109/ICB.2016.7550092ISI: 000390841200046Scopus ID: 2-s2.0-84988421024ISBN: 9781509018697 (print)OAI: oai:DiVA.org:kth-189187DiVA, id: diva2:944055
Conference
ICB 2016 The 9th IAPR International Conference on Biometrics ,June 13-16, 2016. Halmstad, Sweden
Note

QC 20160629

Available from: 2016-06-28 Created: 2016-06-28 Last updated: 2018-03-07Bibliographically approved
In thesis
1. Human Face Identification and Face Attribute Prediction: From Gabor Filtering to Deep Learning
Open this publication in new window or tab >>Human Face Identification and Face Attribute Prediction: From Gabor Filtering to Deep Learning
2016 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

After decades of research, it is exciting to see that face recognition technology has entered a most flourishing era. Driven by the latest development in data science and especially technical evolutions in computer vision and pattern recognition, face recognition has achieved significant progress over the last three years. In the near future, people can expect many useful and interesting face recognition applications to be deployed in many situations: they can be used for identifying suspects, organizing your photos with family and friends, and making computers better understand human beings. Many mysterious face recognition tricks depicted in movies may become reality in several years' time.

This thesis focuses on the development of face recognition algorithms that identify people from a single still image. Two questions are specifically studied. First, it introduces how we identify faces captured in controlled scenarios with cooperative users. In this scenario, a face recognition system captures a face and finds the most similar face from the ones stored in the face recognition system. Second, it describes our solutions for predicting face attributes from faces captured under arbitrary imaging conditions. These two problems were tackled by different schools of technologies: the solution to the first question employed a learning-free approach, whereas the latter question was solved by using the most recent Deep Learning technology. Thus, this thesis also reflects the technological evolution of face recognition over recent years.

To identify faces in controlled scenarios, we propose a novel Block Matching approach, which can effectively match faces without feature engineering or any machine learning components. By representing faces with very concise Gabor phase codes and matching them through our Block Matching approach, the identification accuracy is entirely comparable to and even better than the state-of-the-art. For predicting the attributes from faces captured in the wild, we propose leveraging the off-the-shelf mid-level representations from pre-trained convolutional neural networks. Comparative experiments show that our solution outperforms the previous state-of-the-art solution with a large margin in terms of both accuracy and efficiency. 

The approaches described in this thesis may look different from the ``mainstream''. But, together with the empirical findings, I hope they could provide some insights and update widely adopted concepts for solving related face recognition and computer vision problems.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2016. p. 27
Series
TRITA-CSC-A, ISSN 1653-5723
National Category
Engineering and Technology
Research subject
Media Technology
Identifiers
urn:nbn:se:kth:diva-195092 (URN)978-91-7729-156-5 (ISBN)
Public defence
2016-11-11, K1, 13:00 (English)
Opponent
Supervisors
Note

QC 20161103

Available from: 2016-11-03 Created: 2016-11-01 Last updated: 2016-11-16Bibliographically approved

Open Access in DiVA

fulltext(1431 kB)221 downloads
File information
File name FULLTEXT01.pdfFile size 1431 kBChecksum SHA-512
91fca7de2db6a178941c1a9740b5d924014ea58e7f3e4c682aa30b3221b4970df39aae97fd9ad973c49652dfbfad964e85f9d94f494415a26043bbd5194103c7
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopusConference webpage

Search in DiVA

By author/editor
Zhong, YangSullivan, JosephineLi, Haibo
By organisation
Media Technology and Interaction Design, MIDComputer Vision and Active Perception, CVAP
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 221 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 860 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf