![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Chapter and Conference Paper
Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary Networks
Training neural networks with binary weights and activations is a challenging problem due to the lack of gradients and difficulty of optimization over discrete weights. Many successful experimental results hav...
-
Chapter and Conference Paper
Bias-Variance Tradeoffs in Single-Sample Binary Gradient Estimators
Discrete and especially binary random variables occur in many machine learning models, notably in variational autoencoders with binary latent states and in stochastic binary networks. When learning such models...
-
Chapter and Conference Paper
Stochastic Normalizations as Bayesian Learning
In this work we investigate the reasons why B...
-
Chapter and Conference Paper
MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models
Dense, discrete Graphical Models with pairwise potentials are a powerful class of models which are employed in state-of-the-art computer vision and bio-imaging applications. This work introduces a new MAP-solv...
-
Chapter and Conference Paper
Scalable Full Flow with Learned Binary Descriptors
We propose a method for large displacement optical flow in which local matching costs are learned by a convolutional neural network (CNN) and a smoothness prior is imposed by a conditional random field (CRF). ...
-
Chapter and Conference Paper
Complexity of Discrete Energy Minimization Problems
Discrete energy minimization is widely-used in computer vision and machine learning for problems such as MAP inference in graphical models. The problem, in general, is notoriously intractable, and finding the ...
-
Article
A Distributed Mincut/Maxflow Algorithm Combining Path Augmentation and Push-Relabel
We propose a novel distributed algorithm for the minimum cut problem. Motivated by applications like volumetric segmentation in computer vision, we aim at solving large sparse problems. When the problem does n...
-
Chapter and Conference Paper
Curvature Prior for MRF-Based Segmentation and Shape Inpainting
Most image labeling problems such as segmentation and image reconstruction are fundamentally ill-posed and suffer from ambiguities and noise. Higher-order image priors encode high-level structural dependencies...
-
Chapter and Conference Paper
A Distributed Mincut/Maxflow Algorithm Combining Path Augmentation and Push-Relabel
We present a novel distributed algorithm for the minimum s-t cut problem, suitable for solving large sparse instances. Assuming vertices of the graph are partitioned into several regions, the algorithm performs p...
-
Chapter and Conference Paper
A Higher Order MRF-Model for Stereo-Reconstruction
We consider the task of stereo-reconstruction under the following fairly broad assumptions. A single and continuously shaped object is captured by two uncalibrated cameras. It is assumed, that almost all surfa...