Litcius/Paper detail

Optimal Transport Driven CycleGAN for Unsupervised Learning in Inverse Problems

Byeongsu Sim, Gyutaek Oh, Jeongsol Kim, Chanyong Jung, Jong Chul Ye

2020SIAM Journal on Imaging Sciences65 citationsDOI

Abstract

To improve the performance of classical generative adversarial networks (GANs), Wasserstein generative adversarial networks (WGANs) were developed as a Kantorovich dual formulation of the optimal transport (OT) problem using Wasserstein-1 distance. However, it was not clear how CycleGAN-type generative models can be derived from the OT theory. Here we show that a novel CycleGAN architecture can be derived as a Kantorovich dual OT formulation if a penalized least squares (PLS) cost with deep learning--based inverse path penalty is used as a transportation cost. One of the most important advantages of this formulation is that depending on the knowledge of the forward problem, distinct variations of CycleGAN architecture can be derived: for example, one with two pairs of generators and discriminators, and the other with only a single pair of generator and discriminator. Even for the two generator cases, we show that the structural knowledge of the forward operator can lead to a simpler generator architecture which significantly simplifies the neural network training. The new CycleGAN formulation, which we call the OT-CycleGAN, has been applied for various biomedical imaging problems, such as accelerated magnetic resonance imaging (MRI), super-resolution microscopy, and low-dose X-ray computed tomography (CT). Experimental results confirm the efficacy and flexibility of the theory.

Topics & Concepts

Generator (circuit theory)DiscriminatorComputer scienceFlexibility (engineering)Inverse problemDual (grammatical number)Operator (biology)Generative grammarArtificial neural networkArtificial intelligenceInverseDeep learningAlgorithmMathematicsPhysicsMathematical analysisGeneBiochemistryGeometryArtTelecommunicationsPower (physics)LiteratureQuantum mechanicsTranscription factorRepressorDetectorStatisticsChemistryGenerative Adversarial Networks and Image SynthesisModel Reduction and Neural NetworksAdvanced Image Processing Techniques
Optimal Transport Driven CycleGAN for Unsupervised Learning in Inverse Problems | Litcius