[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
research-article

Learning Person-Specific Representations From Faces in the Wild

Published: 01 December 2014 Publication History

Abstract

Humans are natural face recognition experts, far out-performing current automated face recognition algorithms, especially in naturalistic, “in the wild” settings. However, a striking feature of human face recognition is that we are dramatically better at recognizing highly familiar faces, presumably because we can leverage large amounts of past experience with the appearance of an individual to aid future recognition. Meanwhile, the analogous situation in automated face recognition, where a large number of training examples of an individual are available, has been largely underexplored, in spite of the increasing relevance of this setting in the age of social media. Inspired by these observations, we propose to explicitly learn enhanced face representations on a per-individual basis, and we present two methods enabling this approach. By learning and operating within person-specific representations, we are able to significantly outperform the previous state-of-the-art on PubFig83, a challenging benchmark for familiar face recognition in the wild, using a novel method for learning representations in deep visual hierarchies. We suggest that such person-specific representations aid recognition by introducing an intermediate form of regularization to the problem.

Cited By

View all
  1. Learning Person-Specific Representations From Faces in the Wild

    Recommendations

    Comments

    Please enable JavaScript to view thecomments powered by Disqus.

    Information & Contributors

    Information

    Published In

    cover image IEEE Transactions on Information Forensics and Security
    IEEE Transactions on Information Forensics and Security  Volume 9, Issue 12
    December 2014
    336 pages

    Publisher

    IEEE Press

    Publication History

    Published: 01 December 2014

    Qualifiers

    • Research-article

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)0
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 09 Dec 2024

    Other Metrics

    Citations

    Cited By

    View all
    • (2020)Real-time human cross-race aging-related face appearance detection with deep convolution architectureJournal of Real-Time Image Processing10.1007/s11554-019-00903-917:1(83-93)Online publication date: 1-Feb-2020
    • (2018)Deep Learning for BiometricsACM Computing Surveys10.1145/319061851:3(1-34)Online publication date: 23-May-2018
    • (2017)Multi-channel multi-model feature learning for face recognitionPattern Recognition Letters10.1016/j.patrec.2016.11.02185:C(79-83)Online publication date: 1-Jan-2017
    • (2017)Where is my puppy? Retrieving lost dogs by facial featuresMultimedia Tools and Applications10.1007/s11042-016-3824-176:14(15325-15340)Online publication date: 1-Jul-2017
    • (2016)Local-Gravity-Face (LG-face) for Illumination-Invariant and Heterogeneous Face RecognitionIEEE Transactions on Information Forensics and Security10.1109/TIFS.2016.253004311:7(1412-1424)Online publication date: 5-Apr-2016
    • (2016)Rate-energy-accuracy optimization of convolutional architectures for face recognitionJournal of Visual Communication and Image Representation10.1016/j.jvcir.2015.12.01536:C(142-148)Online publication date: 1-Apr-2016
    • (2015)The Impact of Bio-Inspired Approaches Toward the Advancement of Face RecognitionACM Computing Surveys10.1145/279112148:1(1-33)Online publication date: 10-Aug-2015

    View Options

    View options

    Login options

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media