Skip to Main content Skip to Navigation

Nonconvex Alternating Direction Optimization for Graphs : Inference and Learning

Abstract : This thesis presents our contributions toinference and learning of graph-based models in computervision. First, we propose a novel class of decompositionalgorithms for solving graph and hypergraphmatching based on the nonconvex alternating directionmethod of multipliers (ADMM). These algorithms arecomputationally efficient and highly parallelizable. Furthermore,they are also very general and can be appliedto arbitrary energy functions as well as arbitraryassignment constraints. Experiments show that theyoutperform existing state-of-the-art methods on popularbenchmarks. Second, we propose a nonconvex continuousrelaxation of maximum a posteriori (MAP) inferencein discrete Markov random fields (MRFs). Weshow that this relaxation is tight for arbitrary MRFs.This allows us to apply continuous optimization techniquesto solve the original discrete problem withoutloss in accuracy after rounding. We study two populargradient-based methods, and further propose a more effectivesolution using nonconvex ADMM. Experimentson different real-world problems demonstrate that theproposed ADMM compares favorably with state-of-theartalgorithms in different settings. Finally, we proposea method for learning the parameters of these graphbasedmodels from training data, based on nonconvexADMM. This method consists of viewing ADMM iterationsas a sequence of differentiable operations, whichallows efficient computation of the gradient of the trainingloss with respect to the model parameters, enablingefficient training using stochastic gradient descent. Atthe end we obtain a unified framework for inference andlearning with nonconvex ADMM. Thanks to its flexibility,this framework also allows training jointly endto-end a graph-based model with another model suchas a neural network, thus combining the strengths ofboth. We present experiments on a popular semanticsegmentation dataset, demonstrating the effectivenessof our method.
Complete list of metadatas
Contributor : Abes Star :  Contact
Submitted on : Tuesday, April 2, 2019 - 10:18:08 AM
Last modification on : Thursday, July 9, 2020 - 4:06:04 PM
Long-term archiving on: : Wednesday, July 3, 2019 - 2:06:56 PM


Version validated by the jury (STAR)


  • HAL Id : tel-02087490, version 1



Dien Khuê Lê-Huu. Nonconvex Alternating Direction Optimization for Graphs : Inference and Learning. Signal and Image processing. Université Paris-Saclay, 2019. English. ⟨NNT : 2019SACLC005⟩. ⟨tel-02087490⟩



Record views


Files downloads