Banca de DEFESA: GABRIEL DAHIA FERNANDES

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
STUDENT : GABRIEL DAHIA FERNANDES
DATE: 08/03/2022
TIME: 09:30
LOCAL: https://conferenciaweb.rnp.br/webconf/mauricio-pamplona-segundo
TITLE:

META LEARNING FOR FEW-SHOT ONE-CLASS CLASSIFICATION

KEY WORDS:

Machine Learning, Computer Vision, Meta-Learning

PAGES: 57
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUBÁREA: Metodologia e Técnicas da Computação
SPECIALTY: Processamento Gráfico (Graphics)
SUMMARY:

We propose a method that can perform one-class classification given only a small number of examples from the target class and none from the others. We formulate the learning of meaningful features for one-class classification as a meta-learning problem in which the meta-training stage repeatedly simulates one-class classification, using the classification loss of the chosen algorithm to learn a feature representation. To learn these representations, we require only multiclass data from similar tasks. We show how the SVDD method can be used with our method, and also propose a simpler variant based on Prototypical Networks that obtains comparable performance, indicating that learning feature representations directly from data may be more important than which one-class algorithm we choose. We validate our approach by adapting few-shot classification datasets to the few-shot one-class classification scenario, obtaining similar results to the state-of-the-art of traditional one-class classification, and that improves upon that of one-class classification baselines employed in the few-shot setting. Moreover, as a practical application, we employ our method to the biometric task of on-device face verification. In this scenario, it compares unfavorably to the state-of-the-art metric learning technique.

BANKING MEMBERS:
Externo ao Programa - 1988620 - RUBISLEY DE PAULA LEMES
Externo à Instituição - FABIO AUGUSTO FARIA - UNIFESP
Externo à Instituição - MAURICIO PAMPLONA SEGUNDO