Transfer Learning Decision Forests for Gesture Recognition

Decision forests are an increasingly popular tool in computer vision problems. Their advantages include high computational efficiency, state-of-the-art accuracy and multi-class support. In this paper, we present a novel method for transfer learning which uses decision forests, and we apply it to rec...

Descripción completa

Detalles Bibliográficos
Autores: Goussies, Norberto Adrián, Ubalde, Sebastián, Mejail, Marta Estela
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2014
País:Argentina
Institución:Consejo Nacional de Investigaciones Científicas y Técnicas
Repositorio:CONICET Digital (CONICET)
Idioma:inglés
OAI Identifier:oai:ri.conicet.gov.ar:11336/33149
Acceso en línea:http://hdl.handle.net/11336/33149
Access Level:acceso abierto
Palabra clave:Gesture Recognition
https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
Descripción
Sumario:Decision forests are an increasingly popular tool in computer vision problems. Their advantages include high computational efficiency, state-of-the-art accuracy and multi-class support. In this paper, we present a novel method for transfer learning which uses decision forests, and we apply it to recognize gestures and characters. We introduce two mechanisms into the decision forest framework in order to transfer knowledge from the source tasks to a given target task. The first one is mixed information gain, which is a data-based regularizer. The second one is label propagation, which infers the manifold structure of the feature space. We show that both of them are important to achieve higher accuracy. Our experiments demonstrate improvements over traditional decision forests in the ChaLearn Gesture Challenge and MNIST data set. They also compare favorably against other state-of-the-art classifiers.