TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Multi-task Deep Face Recognition

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoBiometric Recognition - 12th Chinese Conference, CCBR 2017, Proceedings
KustantajaSpringer Verlag
Sivut183-190
Sivumäärä8
ISBN (painettu)9783319699226
DOI - pysyväislinkit
TilaJulkaistu - 2017
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaChinese Conference on Biometric Recognition -
Kesto: 1 tammikuuta 2000 → …

Julkaisusarja

NimiLecture Notes in Computer Science
Vuosikerta10568
ISSN (painettu)0302-9743
ISSN (elektroninen)1611-3349

Conference

ConferenceChinese Conference on Biometric Recognition
Ajanjakso1/01/00 → …

Tiivistelmä

In recent years, deep learning has become one of the most representative and effective techniques in face recognition. Due to the high expense of labelling data, it is costly to collect a large-scale face dataset with accurate label information. For the tasks without sufficient data, deep models cannot be well trained. Generally, parameters of deep models are usually initialized with a pre-trained model, and then fine-tuned on a small dataset of specific task. However, by straightforward fine-tuning, the final model usually does not generalize well. In this paper, we propose a multi-task deep learning (MTDL) method for face recognition. The superiority of the proposed multi-task method is demonstrated by experiments on LFW and CCFD.

Tutkimusalat

Julkaisufoorumi-taso