Robust Deep Face Recognition with Label Noise

Jirui Yuan, Wenya Ma, Pengfei Zhu, Karen Egiazarian

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    2 Citations (Scopus)

    Abstract

    In the last few years, rapid development of deep learning method has boosted the performance of face recognition systems. However, face recognition still suffers from a diverse variation of face images, especially for the problem of face identification. The high expense of labelling data makes it hard to get massive face data with accurate identification information. In real-world applications, the collected data are mixed with severe label noise, which significantly degrades the generalization ability of deep learning models. In this paper, to alleviate the impact of the label noise, we propose a robust deep face recognition (RDFR) method by automatic outlier removal. The noisy faces are automatically recognized and removed, which can boost the performance of the learned deep models. Experiments on large-scale face datasets LFW, CCFD, and COX show that RDFR can effectively remove the label noise and improve the face recognition performance.

    Original languageEnglish
    Title of host publicationNeural Information Processing - 24th International Conference, ICONIP 2017, Proceedings
    PublisherSpringer Verlag
    Pages593-602
    Number of pages10
    ISBN (Print)9783319700953
    DOIs
    Publication statusPublished - 2017
    Publication typeA4 Article in a conference publication
    EventINTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING -
    Duration: 1 Jan 1900 → …

    Publication series

    NameLecture Notes in Computer Science
    Volume10635
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349

    Conference

    ConferenceINTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING
    Period1/01/00 → …

    Keywords

    • Deep learning
    • Face recognition
    • Noise removal

    Publication forum classification

    • Publication forum level 1

    ASJC Scopus subject areas

    • Theoretical Computer Science
    • Computer Science(all)

    Fingerprint

    Dive into the research topics of 'Robust Deep Face Recognition with Label Noise'. Together they form a unique fingerprint.

    Cite this