Separating Self-Expression and Visual Content in Hashtag Supervision

TL;DR

This paper introduces a joint modeling approach that separates self-expressive hashtags from visual content, improving image tagging and retrieval by accounting for user-specific hashtag usage.

Contribution

It proposes a novel joint distribution model of images, hashtags, and users to handle hashtag ambiguity and subjectivity in vision tasks.

Findings

Enhanced image tagging accuracy

Improved user-conditional retrieval

Effective handling of hashtag ambiguity

Abstract

The variety, abundance, and structured nature of hashtags make them an interesting data source for training vision models. For instance, hashtags have the potential to significantly reduce the problem of manual supervision and annotation when learning vision models for a large number of concepts. However, a key challenge when learning from hashtags is that they are inherently subjective because they are provided by users as a form of self-expression. As a consequence, hashtags may have synonyms (different hashtags referring to the same visual content) and may be ambiguous (the same hashtag referring to different visual content). These challenges limit the effectiveness of approaches that simply treat hashtags as image-label pairs. This paper presents an approach that extends upon modeling simple image-label pairs by modeling the joint distribution of images, hashtags, and users. We demonstrate the efficacy of such approaches in image tagging and retrieval experiments, and show how the joint model can be used to perform user-conditional retrieval and tagging.