cs.LGNov 9, 2026

Controlled Binary Assignment Flows

Authors: Paul Fröhling, Christoph Schnörr

Organizations: Institute for Mathematics, Image and Pattern Analysis Group, Heidelberg University, Germany · Research Station Geometry and Dynamics, Heidelberg University

Abstract

This paper introduces a geometric approach to the representation and learning of time-variant parametrizations of deep assignment flows, for binary data labelings on graphs. Each edge carries an optimally controlled parameter flow in a 2-dimensional totally geodesic submanifold, based on objectives derived from a non-local linear scale space representation of the input data. The aggregation of triplets of such flows in 5-dimensional totally geodesic submanifolds is learned from data. The fusion of these flows determines the trajectory in the high-dimensional symmetric parameter space and by geometric integration the layers of binary deep assignment flows. Numerical results demonstrate the expressivity and the limitation of our highly parallel geometric local synthesis approach to high-dimensional deep assignment flow parametrizations.

Figures & tables

Explore similar work

CardsList
  1. Deep learning and the rate of approximation by flows

    Mar 16, 2026Jingpu Cheng, Qianxiao Li, Ting Lin +1Neural Network Approximation TheoryFunction Approximation

  2. What Time Is It? How Data Geometry Makes Time Conditioning Optional for Flow Matching

    May 8, 2026Alec Helbling, Sebastian Gutierrez Hernandez, Benjamin Hoover +2Flow MatchingFlow-Based Generative Modeling