English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/96857
Compartir / Impacto:
Estadísticas
Add this article to your Mendeley library MendeleyBASE
 |  Ver citas en Google académico
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar otros formatos: Exportar EndNote (RIS)Exportar bibText (RIS)Exportar csv (RIS)
Título

Optimization of robust loss functions for weakly-labeled image taxonomies: An ImageNet case study

Autor McAuley, Julian J.; Ramisa, Arnau; Caetano, Tibério S.
Fecha de publicación 2011
EditorSpringer
Citación Energy Minimization Methods in Computer Vision and Pattern Recognition: 355-368 (2011)
Serie Lecture Notes in Computer Science 6819
ResumenThe recently proposed ImageNet dataset consists of several million images, each annotated with a single object category. However, these annotations may be imperfect, in the sense that many images contain multiple objects belonging to the label vocabulary. In other words, we have a multi-label problem but the annotations include only a single label (and not necessarily the most prominent). Such a setting motivates the use of a robust evaluation measure, which allows for a limited number of labels to be predicted and, as long as one of the predicted labels is correct, the overall prediction should be considered correct. This is indeed the type of evaluation measure used to assess algorithm performance in a recent competition on ImageNet data. Optimizing such types of performance measures presents several hurdles even with existing structured output learning methods. Indeed, many of the current state-of-the-art methods optimize the prediction of only a single output label, ignoring this `structure¿ altogether. In this paper, we show how to directly optimize continuous surrogates of such performance measures using structured output learning techniques with latent variables. We use the output of existing binary classifiers as input features in a new learning stage which optimizes the structured loss corresponding to the robust performance measure. We present empirical evidence that this allows us to `boost¿ the performance of existing binary classifiers which are the state-of-the-art for the task of object classification in ImageNet.
Descripción Trabajo presentado a la 8th International Conference EMMCVPR celebrada en St. Petersburg del 25 al 27 de julio de 2011.
Versión del editorhttp://dx.doi.org/10.1007/978-3-642-23094-3_26
URI http://hdl.handle.net/10261/96857
DOI10.1007/978-3-642-23094-3_26
Identificadoresdoi: 10.1007/978-3-642-23094-3_26
isbn: 978-3-642-23093-6
Aparece en las colecciones: (IRII) Libros y partes de libros
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
robust loss functions.pdf3,46 MBUnknownVisualizar/Abrir
Mostrar el registro completo
 


NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.