What makes an Image Iconic? A Fine-Grained Case Study

TL;DR

This study investigates what makes images iconic, demonstrating that iconicity is a consistent, measurable property, and develops models to predict iconicity with accuracy approaching human judgment.

Contribution

The paper provides the first extensive analysis of iconicity in images, showing its objectivity and proposing models to predict iconicity based on visual properties.

Findings

Iconicity ratings are consistent across individuals.

A combination of properties can predict iconicity effectively.

A direct predictor approaches human-level performance.

Abstract

A natural approach to teaching a visual concept, e.g. a bird species, is to show relevant images. However, not all relevant images represent a concept equally well. In other words, they are not necessarily iconic. This observation raises three questions. Is iconicity a subjective property? If not, can we predict iconicity? And what exactly makes an image iconic? We provide answers to these questions through an extensive experimental study on a challenging fine-grained dataset of birds. We first show that iconicity ratings are consistent across individuals, even when they are not domain experts, thus demonstrating that iconicity is not purely subjective. We then consider an exhaustive list of properties that are intuitively related to iconicity and measure their correlation with these iconicity ratings. We combine them to predict iconicity of new unseen images. We also propose a direct iconicity predictor that is discriminatively trained with iconicity ratings. By combining both systems, we get an iconicity prediction that approaches human performance.