Nonlocal regularized cnn for image segmentation

Fan Jia, Xue-Cheng Tai, Jun Liu*

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

7 Citations (Scopus)


Non-local dependency is a very important prior for many image segmentation tasks. Generally, convolutional operations are building blocks that process one local neighborhood at a time which means the convolutional neural networks(CNNs) usually do not explicitly make use of the non-local prior on image segmentation tasks. Though the pooling and dilated convolution techniques can enlarge the receptive field to use some nonlocal information during the feature extracting step, there is no nonlocal priori for feature classification step in the current CNNs’ architectures. In this paper, we present a nonlocal total variation (TV) regularized softmax activation function method for semantic image segmentation tasks. The proposed method can be integrated into the architecture of CNNs. To handle the difficulty of back-propagation for CNNs due to the non-smoothness of nonlocal TV, we develop a primal-dual hy-brid gradient method to realize the back-propagation of nonlocal TV in CNNs. Experimental evaluations of the non-local TV regularized softmax layer on a series of image segmentation datasets showcase its good performance. Many CNNs can benefit from our proposed method on image segmentation tasks.

Original languageEnglish
Pages (from-to)891-911
Number of pages21
JournalInverse Problems and Imaging
Issue number5
Early online dateJul 2020
Publication statusPublished - Oct 2020

Scopus Subject Areas

  • Analysis
  • Modelling and Simulation
  • Discrete Mathematics and Combinatorics
  • Control and Optimization

User-Defined Keywords

  • CNN
  • Duality
  • Image segmentation
  • Nonlocal TV
  • Regularization


Dive into the research topics of 'Nonlocal regularized cnn for image segmentation'. Together they form a unique fingerprint.

Cite this