The assignment flow is a dynamical system that evolves on an elementary statistical manifold and performs image labeling, i.e.~context-sensitive image classification. It provides a smooth and computationally efficient alternative to non-smooth discrete graphical models and enables to study basic problems related to the design and understanding of larger compositional systems for image analysis: supervised labeling, unsupervised label learning and representation learning using optimal control. The talk reports the mathematical ingredients (information theory, discrete optimal transport, geometric integration), recent results and perspectives.
Copyright. All Rights Reserved.