Analyzing structural characteristics of object category representations from their semantic-part distributions

TL;DR

This paper introduces a method to analyze the semantic-part distribution in object category representations using sketch-based epitomes, revealing structural trends and part importance in visual recognition.

Contribution

It presents a novel approach to analyze semantic-part characteristics in object representations through sketch-based epitomes and visualization techniques.

Findings

Semantic parts are variably present in epitomes across categories.

Word cloud visualizations reveal structural trends in object categories.

Part importance insights align with human visual recognition processes.

Abstract

Studies from neuroscience show that part-mapping computations are employed by human visual system in the process of object recognition. In this work, we present an approach for analyzing semantic-part characteristics of object category representations. For our experiments, we use category-epitome, a recently proposed sketch-based spatial representation for objects. To enable part-importance analysis, we first obtain semantic-part annotations of hand-drawn sketches originally used to construct the corresponding epitomes. We then examine the extent to which the semantic-parts are present in the epitomes of a category and visualize the relative importance of parts as a word cloud. Finally, we show how such word cloud visualizations provide an intuitive understanding of category-level structural trends that exist in the category-epitome object representations.