Learning Linearized Assignment Flows for Image Labeling
We introduce a novel algorithm for estimating optimal parameters of linearized assignment flows for image labeling. An exact formula is derived for the parameter gradient of any loss function that is constrained by the linear system of ODEs determining the linearized assignment flow. We show how to efficiently evaluate this formula using a Krylov subspace and a low-rank approximation. This enables us to perform parameter learning by Riemannian gradient descent in the parameter space, without the need to backpropagate errors or to solve an adjoint equation. Experiments demonstrate that our method performs as good as highly-tuned machine learning software using automatic differentiation. Unlike methods employing automatic differentiation, our approach yields a low-dimensional representation of internal parameters and their dynamics which helps to understand how assignment flows and more generally neural networks work and perform.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Riemannian Patch Assignment Gradient Flows
This paper introduces patch assignment flows for metric data labeling on graphs. Labelings are determined by regularizing initial local labelings through the dynamic interaction of both labels and label assignments acros…
Numerical IntegrationUncertainty QuantificationUnsupervised Assignment Flow: Label Learning on Feature Manifolds by Spatially Regularized Geometric Assignment
This paper introduces the unsupervised assignment flow that couples the assignment flow for supervised image labeling with Riemannian gradient flows for label evolution on feature manifolds. The latter component of the a…
ClusteringSelf-Assignment Flows for Unsupervised Data Labeling on Graphs
This paper extends the recently introduced assignment flow approach for supervised image labeling to unsupervised scenarios where no labels are given. The resulting self-assignment flow takes a pairwise data affinity mat…
Combinatorial OptimizationSelf-Certifying Classification by Linearized Deep Assignment
We propose a novel class of deep stochastic predictors for classifying metric data on graphs within the PAC-Bayes risk certification paradigm. Classifiers are realized as linearly parametrized deep assignment flows with …
ClassificationGenerative Assignment Flows for Representing and Learning Joint Distributions of Discrete Data
We introduce a novel generative model for the representation of joint probability distributions of a possibly large number of discrete random variables. The approach uses measure transport by randomized assignment flows …