Object-Centric Anomaly Detection by Attribute-Based Reasoning

Babak Saleh, Ali Farhadi, Ahmed Elgammal; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 787-794

Abstract


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 also show that abnormality predictions can help image categorization. We introduce the abnormality detection dataset and show interesting results on how to reason about abnormalities.

Related Material


[pdf]
[bibtex]
@InProceedings{Saleh_2013_CVPR,
author = {Saleh, Babak and Farhadi, Ali and Elgammal, Ahmed},
title = {Object-Centric Anomaly Detection by Attribute-Based Reasoning},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}