Abnormal Object Recognition: A Comprehensive Study
This addresses the challenge of identifying interesting or abnormal elements in images for applications like image description and recognition.
The paper tackles the problem of recognizing abnormalities in images by modeling typicalities and deviations from prototypical properties, introducing a dataset and showing results on reasoning about abnormalities.
When describing images, humans tend not to talk about the obvious, but rather mention what they find interesting. We argue that abnormalities and deviations from typicalities are among the most important components that form what is worth mentioning. In this paper we introduce the abnormality detection as a recognition problem and show how to model typicalities and, consequently, meaningful deviations from prototypical properties of categories. Our model can recognize abnormalities and report the main reasons of any recognized abnormality. We introduce the abnormality detection dataset and show interesting results on how to reason about abnormalities.