Simple Tag-based Subclass Representations for Visually-varied Image Classes

Conference paper (2016)

Authors

X. Li

P. Xu Pattern Recognition and Bioinformatics -

Y. Shi Yahoo! Labs

M.A. Larson , Radboud Universiteit Nijmegen

A. Hanjalic

Multimedia communication Visualization Training Predictive models Support vector machines Flickr Tagging

To reference this document use:

http://resolver.tudelft.nl/uuid:dac2a63e-12c4-40db-97c5-21244d441fa4

More Info

expand_more

Published Date

30-06-2016

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

In this paper, we present a subclass-representation approach that predicts the probability of a social image belonging to one particular class. We explore the co-occurrence of user-contributed tags to find subclasses with a strong connection to the top level class. We then project each image onto the resulting subclass space, generating a subclass representation for the image. The advantage of our tag-based subclasses is that they have a chance of being more visually stable and easier to model than top-level classes. Our contribution is to demonstrate that a simple and inexpensive method for generating sub-class representations has the ability to improve classification results in the case of tag classes that are visually highly heterogenous. The approach is evaluated on a set of 1 million photos with 10 top-level classes, from the dataset released by the ACM Multimedia 2013 Yahoo! Large-scale Flickr-tag Image Classification Grand Challenge. Experiments show that the proposed system delivers sound performance for visually diverse classes compared with methods that directly model top classes.