CVJul 8, 2022
Continuous Methods : Hamiltonian Domain Translation
arXiv:2207.03843v11 citationsh-index: 18
Originality Incremental advance
AI Analysis
This work addresses domain translation for machine learning applications, presenting an incremental improvement through a novel architectural reformulation.
The authors tackled the problem of domain translation by reformulating Cycle-GAN with a Hamiltonian structure, resulting in a continuous, expressive, and invertible generative model.
This paper proposes a novel approach to domain translation. Leveraging established parallels between generative models and dynamical systems, we propose a reformulation of the Cycle-GAN architecture. By embedding our model with a Hamiltonian structure, we obtain a continuous, expressive and most importantly invertible generative model for domain translation.