Learning Subclass Representations for Visually-varied Image Classification

by   Xinchao Li, et al.

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 on to the resulting subclass space to generate a subclass representation for the image. The novelty of the approach is that subclass representations make use of not only the content of the photos themselves, but also information on the co-occurrence of their tags, which determines membership in both subclasses and top-level classes. The novelty is also that the images are classified into smaller classes, which have a chance of being more visually stable and easier to model. These subclasses are used as a latent space and images are represented in this space by their probability of relatedness to all of the subclasses. In contrast to approaches directly modeling each top-level class based on the image content, the proposed method can exploit more information for visually diverse classes. The approach is evaluated on a set of 2 million photos with 10 classes, released by the 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.


page 1

page 4


Image Classification and Retrieval from User-Supplied Tags

This paper proposes direct learning of image classification from user-su...

Who Let The Dogs Out? Modeling Dog Behavior From Visual Data

We introduce the task of directly modeling a visually intelligent agent....

Constructing Hierarchical Image-tags Bimodal Representations for Word Tags Alternative Choice

This paper describes our solution to the multi-modal learning challenge ...

A Web Page Classifier Library Based on Random Image Content Analysis Using Deep Learning

In this paper, we present a methodology and the corresponding Python lib...

Empowering Visually Impaired Individuals: A Novel Use of Apple Live Photos and Android Motion Photos

Numerous applications have been developed to assist visually impaired in...

Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification

Many advances of deep learning techniques originate from the efforts of ...

On environments as systemic exoskeletons: Crosscutting optimizers and antifragility enablers

Classic approaches to General Systems Theory often adopt an individual p...

Please sign up or login with your details

Forgot password? Click here to reset