Deep learning of robust representations for multi-instance and multi-label image classification

In multi-instance problems (MIL), an arbitrary number of instances is associated with a class label. Therefore, the labeling of training data becomes simpler (since it is done together, instead of individually) with the disadvantage that a weakly supervised database is produced [9]. In the PCRY, eac...

Full description

Autores:
Silva, Jesús
Varela Izquierdo, Noel
Mendoza Palechor, Fabio
Pineda, Omar
Tipo de recurso:
http://purl.org/coar/resource_type/c_816b
Fecha de publicación:
2020
Institución:
Corporación Universidad de la Costa
Repositorio:
REDICUC - Repositorio CUC
Idioma:
eng
OAI Identifier:
oai:repositorio.cuc.edu.co:11323/7257
Acceso en línea:
https://hdl.handle.net/11323/7257
https://repositorio.cuc.edu.co/
Palabra clave:
Deep learning
Image classification
Multi-instance
Multi-label
Rights
closedAccess
License
Attribution-NonCommercial-NoDerivatives 4.0 International
Description
Summary:In multi-instance problems (MIL), an arbitrary number of instances is associated with a class label. Therefore, the labeling of training data becomes simpler (since it is done together, instead of individually) with the disadvantage that a weakly supervised database is produced [9]. In the PCRY, each restaurant is represented by a set of images that share the attribute label(s) of that establishment. This paper explores the use of previously learned attribute extractors, trained in 3 different databases that are similar and complementary to the PCRY database