Abstract
I will be talking about our work in anomaly detection targeting real-world scenarios in product
quality assessment. I will introduce three new anomaly detection tasks along with their benchmarks
and customized solutions that enable clear definition of normality and accurate detection of
anomalies. Our techniques will include 3D modelling objects from multiple views and learning
correspondences for aligning them. I will also discuss an active anomaly detection technique that
goes beyond over anomaly detection techniques from passive observations.
Biography
Hakan Bilen is an associate professor in the School of Informatics at the University of
Edinburgh and leading the Visual Computing research group since 2017. He completed his PhD in
the VISICS group of KU Leuven and worked as a post-doc in the Visual Geometry Group at the
University of Oxford. He is currently interested in the intersection of computer vision and machine
learning with a focus on anomaly detection, 3D understanding and interpretability.
For publications, please see
https://scholar.google.com/citations?hl=en&user=PtBtfawAAAAJ&view_op=list_works