# Learning Subclass Representations for Visually-varied Image Classification

Source: [Learning Subclass Representations for Visually-varied Image Classification](<https://www.sota2.com/research/paper/68fa62461e209131ce9f876d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T05:50:53.268Z

Authors: Xinchao Li, Peng Xu, Yue Shi, Martha Larson, Alan Hanjalic

Published: 2016-01-12T15:30:58.000Z

## 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 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1601.02913>)

[PDF](<https://arxiv.org/pdf/1601.02913.pdf>)