Maximum likelihood features for generative image models

Maximum-Likelihood Augmented Discrete Generative Adversarial Networks

Despite the successes in capturing continuous distributions, the application of generative adversarial networks (GANs) to discrete settings, like natural language tasks, is rather restricted. The fundamental reason is the difficulty of backpropagation through discrete random variables combined with the inherent instability of the GAN training objective. To address these problems, we propose Max...

Maximum-Likelihood Image Matching

ÐImage matching applications such as tracking and stereo commonly use the sum-of-squared-difference (SSD) measure to determine the best match. However, this measure is sensitive to outliers and is not robust to template variations. Alternative measures have also been proposed that are more robust to these issues. We improve upon these using a probabilistic formulation for image matching in term...

A comparison of algorithms for maximum likelihood estimation of Spatial GLM models

In spatial generalized linear mixed models, spatial correlation is assumed by adding normal latent variables to the model. In these models because of the non-Gaussian spatial response and the presence of latent variables the likelihood function cannot usually be given in a closed form, thus the maximum likelihood approach is very challenging. The main purpose of this paper is to introduce two n...

Boosting and Maximum Likelihood for Exponential Models

We derive an equivalence between AdaBoost and the dual of a convex optimization problem, showing that the only difference between minimizing the exponential loss used by AdaBoost and maximum likelihood for exponential models is that the latter requires the model to be normalized to form a conditional probability distribution over labels. In addition to establishing a simple and easily understoo...

Boosting and Maximum Likelihood for Exponential Models