Random k-Labelsets for Multilabel Classification

Tsoumakas, Grigorios; Katakis, Ioannis; Vlahavas, Ioannis

doi:10.1109/tkde.2010.164

Cited by 775 publications

(457 citation statements)

References 23 publications

Supporting

Mentioning

423

Contrasting

Unclassified

Order By: Relevance

“…One of the baseline approaches to multi-label classification is a problem transformation method: Label Powerset (LP) (Tsoumakas et al, 2011). The LP approach explores all possible label combinations.…”

Section: The Facial Attributes Powerset For Classificationmentioning

confidence: 99%

Robust gender recognition by exploiting facial attributes dependencies

Bekios-Calfa

Buenaposada

Baumela

2014

Pattern Recognition Letters

View full text Add to dashboard Cite

Estimating human face gender from images is a problem that has been extensively studied because of its relevant applications. Recent works report significant drops in performance for state-of-the-art gender classifiers when evaluated "in the wild," i.e. with uncontrolled demography and environmental conditions. We hypothesize that this is caused by the existence of dependencies among facial demographic attributes that have not been considered when building the classifier. In the paper we study the dependencies among gender, age and pose facial attributes. By considering the relation between gender and pose attributes we also avoid the use of computationally expensive and fragile face alignment procedures. In the experiments we confirm the existence of dependencies among gender, age and pose facial attributes and prove that we can improve the performance and robustness of gender classifiers by exploiting these dependencies.

show abstract

Section: The Facial Attributes Powerset For Classificationmentioning

confidence: 99%

Robust gender recognition by exploiting facial attributes dependencies

Bekios-Calfa

Buenaposada

Baumela

2014

Pattern Recognition Letters

View full text Add to dashboard Cite

show abstract

“…Multiclassifier systems proved to be an efficient tool for solving classification problems across domains such as bioinformatics (Plumpton, 2014;Fraz et al, 2012), economy (Hsieh and Hung, 2010) and many more (Wozniak et al, 2014). Ensemble systems have been extensively adopted to machine learning problems such as multi-label learning (Tsoumakas et al, 2010) and on-line learning (Plumpton, 2014).…”

Section: Introductionmentioning

confidence: 99%

A dynamic model of classifier competence based on the local fuzzy confusion matrix and the random reference classifier

Trajdos

Kurzyński

2016

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

Nowadays, multiclassifier systems (MCSs) are being widely applied in various machine learning problems and in many different domains. Over the last two decades, a variety of ensemble systems have been developed, but there is still room for improvement. This paper focuses on developing competence and interclass cross-competence measures which can be applied as a method for classifiers combination. The cross-competence measure allows an ensemble to harness pieces of information obtained from incompetent classifiers instead of removing them from the ensemble. The cross-competence measure originally determined on the basis of a validation set (static mode) can be further easily updated using additional feedback information on correct/incorrect classification during the recognition process (dynamic mode). The analysis of computational and storage complexity of the proposed method is presented. The performance of the MCS with the proposed cross-competence function was experimentally compared against five reference MCSs and one reference MCS for static and dynamic modes, respectively. Results for the static mode show that the proposed technique is comparable with the reference methods in terms of classification accuracy. For the dynamic mode, the system developed achieves the highest classification accuracy, demonstrating the potential of the MCS for practical applications when feedback information is available.

show abstract

“…Assim, existe a possibilidade de um algoritmo de aprendizado unirrótulo construir os classificadores individualmente. Existem na literatura diversos métodos capazes de transformar problemas de classificação multirrótulos em problemas de classificação unirrótulo, dentre eles os métodos BR (Binary Relevance), LP (Label Powerset) e RAkEL (RAndom k-LabELsets) [32].…”

Section: Métodos De Transformação Do Problemaunclassified

“…Um dos seus objetivos é minimizar os problemas oriundos do LP, pois mesmo considerando a correlação entre os rótulos, busca-se coibir o problema da suscetibilidade ao surgimento de muitas classes com uma quantidade mínima de exemplos. Foi proposta uma abordagem em [32] onde um parâmetro definido k especifica o tamanho do subconjunto de rótulos que devem ser considerados [34].…”

Section: Rakelunclassified

Estratégias de Construções de Comitês de Classificadores Multirrótulos no Aprendizado Semissupervisionado Multidescrição

Silva

Santos

2017

RITA

View full text Add to dashboard Cite

Resumo: Classificação multirrótulo é um problema de aprendizado supervisionado no qual um objeto pode estar associado a múltiplas classes. Dentre os diferentes métodos de classificação multirrótulo destacam-se os métodos BR (Binary Relevance), LP (Label Powerset) e RAkEL (RAndom k-labELsets). O trabalho realizou um estudo sobre as construções de comitês de classificadores multirrótulos construídos através da aplicação de técnicas de aprendizado semissupervisionado multidescrição. Os comitês de classificadores utilizados nos experimentos foram o Bagging, Boosting e Stacking; como métodos de transformação do problema utilizamos os métodos BR, LP e Rakel; na classificação multirrótulo semissupervisionada multidescrição foi utilizado o Co-Training; foram aplicados cinco diferentes algoritmos como classificadores base: k-NN (k Vizinhos Mais Próximos), J48 (Algoritmo de Indução de Árvores de Decisão), SVM (Máquinas de Vetores Suporte), NB (Naive Bayes) e o JRip (Extended Repeated Incremental Pruning). Todos os experimentos utilizaram a metodologia de validação cruzada com 10 grupos (10-fold Cross-Validation) e o framework MULAN, o qual é implementado utilizando o WEKA. Para os tamanhos dos comitês de classificadores adotamos os valores 3, 5, 7 e 9. Para a análise dos resultados foi utilizado o teste estatístico de Wilcoxon. Ao final das análises experimentais, verificou-se que a abordagem semissupervisionado apresentou resultados competitivos em relação ao aprendizado supervisionado, uma vez que as duas abordagens utilizadas apresentaram resultados estatisticamente semelhantes.

show abstract

Random k-Labelsets for Multilabel Classification

Cited by 775 publications

References 23 publications

Robust gender recognition by exploiting facial attributes dependencies

Robust gender recognition by exploiting facial attributes dependencies

A dynamic model of classifier competence based on the local fuzzy confusion matrix and the random reference classifier

Estratégias de Construções de Comitês de Classificadores Multirrótulos no Aprendizado Semissupervisionado Multidescrição

Contact Info

Product

Resources

About