English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/96857
Share/Impact:
Statistics
logo share SHARE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
Exportar a otros formatos:

Title

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

AuthorsMcAuley, Julian J.; Ramisa, Arnau ; Caetano, Tibério S.
Issue Date2011
PublisherSpringer
CitationEnergy Minimization Methods in Computer Vision and Pattern Recognition: 355-368 (2011)
SeriesLecture Notes in Computer Science 6819
AbstractThe 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.
DescriptionTrabajo presentado a la 8th International Conference EMMCVPR celebrada en St. Petersburg del 25 al 27 de julio de 2011.
Publisher version (URL)http://dx.doi.org/10.1007/978-3-642-23094-3_26
URIhttp://hdl.handle.net/10261/96857
DOIhttp://dx.doi.org/10.1007/978-3-642-23094-3_26
Identifiersdoi: 10.1007/978-3-642-23094-3_26
isbn: 978-3-642-23093-6
Appears in Collections:(IRII) Libros y partes de libros
Files in This Item:
File Description SizeFormat 
robust loss functions.pdf3,46 MBUnknownView/Open
Show full item record
Review this work
 


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.