… deep learning techniques in matching problems, we present a method for learning context-aware
features for solving optical flow using discrete … data term for discrete MAP inference in a …

… Experiments suggest that over simple deep neural networks, gradient descent with … flow.
We hypothesize that the theory of gradient flows will unravel mysteries behind deep learning.…

… discrete flows on a number of controlled problems: discretized mixture of Gaussians, full-rank
discrete … In all settings, we find that stacking discrete autoregressive flows yields improved …

… ) using a deep neural network framework. More specifically, we first propose discrete gradient
flow … (1998), we consider the second class of discrete gradient flows for special classes of …

… matching and discrete flows that provides a large design space of discrete non-autoregressive
generative models. Searching within this space we were able to train large scale …

… flow from a discrete point of view. Motivated by the observation that sub-pixel accuracy is
easily obtained given pixel-accurate optical flow, … optical flow estimation as a discrete inference …

… a flow-based generative model for ordinal discrete data called Integer Discrete Flow (IDF): a
… data that can be used for deep generative modelling and neural lossless compression. We …

… We consider the problem of molecular graph generation using deep models. While graphs
are discrete, most existing methods use continuous latent variables, resulting in inaccurate …

… and irregularities in traffic flow data. This article proposes a deep-space time traffic flow
prediction model based on discrete wavelet transform (DSTM-DWT) to overcome the highly …

… deep veins valves is modelled by means of discrete multi-physics and an agglomeration
algorithm is implemented to account for blood accrual in the flow. … stagnation in the flow. Rigid …