Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Transferring from face recognition to face attribute prediction through adaptive selection of off-the-shelf CNN representations
KTH, Skolan för datavetenskap och kommunikation (CSC), Robotik, perception och lärande, RPL.ORCID-id: 0000-0002-8673-0797
KTH, Skolan för datavetenskap och kommunikation (CSC), Robotik, perception och lärande, RPL.
KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.ORCID-id: 0000-0003-3779-5647
2016 (Engelska)Ingår i: 2016 23rd International Conference on Pattern Recognition, ICPR 2016, Institute of Electrical and Electronics Engineers (IEEE), 2016, s. 2264-2269, artikel-id 7899973Konferensbidrag (Refereegranskat)
Abstract [en]

This paper addresses the problem of transferring CNNs pre-trained for face recognition to a face attribute prediction task. To transfer an off-the-shelf CNN to a novel task, a typical solution is to fine-tune the network towards the novel task. As demonstrated in the state-of-the-art face attribute prediction approach, fine-tuning the high-level CNN hidden layer by using labeled attribute data leads to significant performance improvements. In this paper, however, we tackle the same problem but through a different approach. Rather than using an end-to-end network, we select face descriptors from off-the-shelf hierarchical CNN representations for recognizing different attributes. Through such an adaptive representation selection, even without any fine-tuning, our results still outperform the state-of-the-art face attribute prediction approach on the latest large-scale dataset for an error rate reduction of more than 20%. Moreover, by using intensive empirical probes, we have identified several key factors that are significant for achieving promising face attribute prediction performance. These results attempt to gain and update our understandings of the nature of CNN features and how they can be better applied to the transferred novel tasks.

Ort, förlag, år, upplaga, sidor
Institute of Electrical and Electronics Engineers (IEEE), 2016. s. 2264-2269, artikel-id 7899973
Serie
International Conference on Pattern Recognition, ISSN 1051-4651
Nationell ämneskategori
Datorteknik
Identifikatorer
URN: urn:nbn:se:kth:diva-215409DOI: 10.1109/ICPR.2016.7899973ISI: 000406771302043Scopus ID: 2-s2.0-85019109911ISBN: 978-1-5090-4847-2 (tryckt)OAI: oai:DiVA.org:kth-215409DiVA, id: diva2:1148103
Konferens
23rd International Conference on Pattern Recognition, ICPR 2016, Cancun CenterCancun, Mexico, 4 December 2016 through 8 December 2016
Anmärkning

QC 20171010

Tillgänglig från: 2017-10-10 Skapad: 2017-10-10 Senast uppdaterad: 2018-01-13Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Sök vidare i DiVA

Av författaren/redaktören
Zhong, YangSullivan, JosephineLi, Haibo
Av organisationen
Robotik, perception och lärande, RPLMedieteknik och interaktionsdesign, MID
Datorteknik

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 43 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf