Flexibly regularized mixture models and application to image segmentation

  title={Flexibly regularized mixture models and application to image segmentation},
  author={Jonathan Vacher and Claire Launay and Ruben Coen-Cagli},
  journal={Neural networks : the official journal of the International Neural Network Society},



Normalization and pooling in hierarchical models of natural images

Location Dependent Dirichlet Processes

This paper proposes location dependent Dirichlet processes (LDDP) which incorporate nonparametric Gaussian processes in the DP modeling framework to model such dependencies.

A Bayesian Framework for Image Segmentation With Spatially Varying Mixtures

A new Bayesian model is proposed for image segmentation based upon Gaussian mixture models (GMM) with spatial smoothness constraints that exploits the Dirichlet compound multinomial (DCM) probability density and a Gauss-Markov random field on theDirichlet parameters to impose smoothness.

Expectation maximization as message passing

It is shown how expectation maximization (EM) may be viewed, and used, as a message passing algorithm in factor graphs.

Texture Interpolation for Probing Visual Perception

It is shown that distributions of deep convolutional neural network activations of a texture are well described by elliptical distributions and therefore, following optimal transport theory, constraining their mean and covariance is sufficient to generate new texture samples.

Recurrent neural circuits for contour detection

This study suggests that the orientation-tilt illusion is a byproduct of neural circuits that help biological visual systems achieve robust and efficient contour detection, and that incorporating these circuits in artificial neural networks can improve computer vision.

Image Segmentation Using Deep Learning: A Survey

A comprehensive review of recent pioneering efforts in semantic and instance segmentation, including convolutional pixel-labeling networks, encoder-decoder architectures, multiscale and pyramid-based approaches, recurrent networks, visual attention models, and generative models in adversarial settings are provided.

Beyond the feedforward sweep: feedback computations in the visual cortex

  • G. KreimanT. Serre
  • Computer Science, Biology
    Annals of the New York Academy of Sciences
  • 2020
An overview of recent work in cognitive neuroscience and machine vision is provided that highlights the possible role of feedback processes for both visual recognition and beyond and discusses important open questions for future research.

Recursive Cascaded Networks for Unsupervised Medical Image Registration

This work presents recursive cascaded networks, a general architecture that enables learning deep cascades, for deformable image registration, and demonstrates that these networks achieve consistent, significant gains and outperform state-of-the-art methods.

Comparing partitions

The problem of comparing two different partitions of a finite set of objects reappears continually in the clustering literature. We begin by reviewing a well-known measure of partition correspondence