A regularized convolutional neural network for semantic image segmentation
From MaRDI portal
Abstract: Convolutional neural networks (CNNs) show outstanding performance in many image processing problems, such as image recognition, object detection and image segmentation. Semantic segmentation is a very challenging task that requires recognizing, understanding what's in the image in pixel level. Though the state of the art has been greatly improved by CNNs, there is no explicit connections between prediction of neighbouring pixels. That is, spatial regularity of the segmented objects is still a problem for CNNs. In this paper, we propose a method to add spatial regularization to the segmented objects. In our method, the spatial regularization such as total variation (TV) can be easily integrated into CNN network. It can help CNN find a better local optimum and make the segmentation results more robust to noise. We apply our proposed method to Unet and Segnet, which are well established CNNs for image segmentation, and test them on WBC, CamVid and SUN-RGBD datasets, respectively. The results show that the regularized networks not only could provide better segmentation results with regularization effect than the original ones but also have certain robustness to noise.
Recommendations
- Nonlocal regularized CNN for image segmentation
- Subset selection for visualization of relevant image fractions for deep learning based semantic image segmentation
- scientific article; zbMATH DE number 2062640
- Convolutional Networks Can Learn to Generate Affinity Graphs for Image Segmentation
- A deep fully residual convolutional neural network for segmentation in EM images
Cites work
- An algorithm for total variation minimization and applications
- Augmented Lagrangian method, dual methods, and split Bregman iteration for ROF, vectorial TV, and high order models
- Image recovery via total variation minimization and related problems
- Nonlinear total variation based noise removal algorithms
- Techniques for gradient-based bilevel optimization with non-smooth lower level problems
Cited in
(24)- Subset selection for visualization of relevant image fractions for deep learning based semantic image segmentation
- Smoothed dilated convolutions for improved dense prediction
- Deep convolutional neural networks with spatial regularization, volume and star-shape priors for image segmentation
- Quasiconformal model with CNN features for large deformation image registration
- Nonlocal regularized CNN for image segmentation
- Enforcing geometrical priors in deep networks for semantic segmentation applied to radiotherapy planning
- A distance function based cascaded neural network for accurate polyps segmentation and classification
- Discrete-time CNN for image segmentation by active contours
- Semantic-based regularization for learning and inference
- Convolutional Networks Can Learn to Generate Affinity Graphs for Image Segmentation
- scientific article; zbMATH DE number 7109071 (Why is no real title available?)
- Revisiting Deep Structured Models for Pixel-Level Labeling with Gradient-Based Inference
- A weighted difference of anisotropic and isotropic total variation for relaxed Mumford-Shah color and multiphase image segmentation
- Cauchy noise removal via convergent plug-and-play framework with outliers detection
- Reaction-diffusion model applied to enhancing U-net accuracy for semantic image segmentation
- Vision graph U-Net: geometric learning enhanced encoder for medical image segmentation and restoration
- Graphmax for text generation
- Variational models and their combinations with deep learning in medical image segmentation: a survey
- Spatially regularized Leaky ReLU in dual space for CNN based image segmentation
- Convex shape prior for deep convolution neural network-based image segmentation
- A trainable variational Chan-Vese network based on algorithm unfolding for image segmentation
- Regularized CNN with geodesic active contour and edge predictor for image segmentation
- Topology-guaranteed image segmentation: enforcing connectivity, genus, and width constraints
- Exponentially-Krill Herd algorithm-based hybrid deep architecture for semantic image segmentation
Describes a project that uses
Uses Software
This page was built for publication: A regularized convolutional neural network for semantic image segmentation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5856266)
