Contour-Aware Equipotential earning for Semantic Segmentation

Xu Yin, Dongbo Min, Yuchi Huo, Sung Eui Yoon

Research output: Contribution to journalArticlepeer-review

Abstract

With increasing demands for high-quality semantic segmentation in the industry, hard-distinguishing semantic boundaries have posed a significant threat to existing solutions. Inspired by real-life experience, i.e., combining varied observations contributes to higher visual recognition confidence, we present the equipotential learning (EPL) method. This novel module transfers the predicted/ground-truth semantic labels to a self-defined potential domain to learn and infer decision boundaries along customized directions. The conversion to the potential domain is implemented via a lightweight differentiable anisotropic convolution that neither incurs the parameter overhead of the neural networks nor changes to the architectures. Besides, the designed two loss functions, the point loss and the equipotential line loss implement anisotropic field regression and category-level contour learning, respectively, enhancing prediction consistencies in the inter/intra-class boundary areas. More importantly, EPL is agnostic to network architectures, and thus it can be plugged into most existing segmentation models. This paper is the first attempt to address the boundary segmentation problem with field regression and contour learning. Meaningful performance improvements on Pascal Voc 2012 and Cityscapes demonstrate that the proposed EPL module can benefit the off-the-shelf fully convolutional network models when recognizing semantic boundary areas. Besides, intensive comparisons and analysis show the favorable merits of EPL for distinguishing semantically-similar and irregular-shaped categories.

Original languageEnglish
Pages (from-to)1-11
Number of pages11
JournalIEEE Transactions on Multimedia
DOIs
StateAccepted/In press - 2022

Keywords

  • Category-level contour learning
  • Convolution
  • Estimation
  • Image segmentation
  • Potential energy
  • Semantic boundary refinement
  • Semantics
  • Supervised Semantic Segmentation
  • Training
  • Visualization

Fingerprint

Dive into the research topics of 'Contour-Aware Equipotential earning for Semantic Segmentation'. Together they form a unique fingerprint.

Cite this