TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Robust Deep Face Recognition with Label Noise

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoNeural Information Processing - 24th International Conference, ICONIP 2017, Proceedings
KustantajaSpringer Verlag
Sivut593-602
Sivumäärä10
ISBN (painettu)9783319700953
DOI - pysyväislinkit
TilaJulkaistu - 2017
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaINTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING -
Kesto: 1 tammikuuta 1900 → …

Julkaisusarja

NimiLecture Notes in Computer Science
Vuosikerta10635
ISSN (painettu)0302-9743
ISSN (elektroninen)1611-3349

Conference

ConferenceINTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING
Ajanjakso1/01/00 → …

Tiivistelmä

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.

Tutkimusalat

Julkaisufoorumi-taso