Semantic-enriched Visual Vocabulary Construction in a Weakly Supervised Context

TL;DR

This paper proposes methods to enrich image representations with semantic information using external labels in a weakly supervised setting, improving classification performance without altering learning algorithms.

Contribution

It introduces two novel approaches for semantic enrichment of visual vocabularies in weakly supervised image classification tasks.

Findings

Semantic enrichment improves classification accuracy.

Filtering irrelevant features enhances performance.

External knowledge integration benefits weakly supervised learning.

Abstract

One of the prevalent learning tasks involving images is content-based image classification. This is a difficult task especially because the low-level features used to digitally describe images usually capture little information about the semantics of the images. In this paper, we tackle this difficulty by enriching the semantic content of the image representation by using external knowledge. The underlying hypothesis of our work is that creating a more semantically rich representation for images would yield higher machine learning performances, without the need to modify the learning algorithms themselves. The external semantic information is presented under the form of non-positional image labels, therefore positioning our work in a weakly supervised context. Two approaches are proposed: the first one leverages the labels into the visual vocabulary construction algorithm, the result being dedicated visual vocabularies. The second approach adds a filtering phase as a pre-processing of the vocabulary construction. Known positive and known negative sets are constructed and features that are unlikely to be associated with the objects denoted by the labels are filtered. We apply our proposition to the task of content-based image classification and we show that semantically enriching the image representation yields higher classification performances than the baseline representation.