2014/11/09 by Babak Saleh, Ali Farhadi, Saleh, Babak +3
Computer Science · Psychology · #Abnormality #Advanced Image and Video Retrieval Techniques #Anomaly Detection Techniques and Applications #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Object (grammar) #Psychology #Social psychology #cs.CV
paper · pdf · doi:10.48550/arxiv.1411.2214
arxiv created 2014/11/09 · openalex publication_date 2014/11/09 · arxiv updated 2014/11/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
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.