Contour-Aware Equipotential Learning for Semantic Segmentation

TL;DR

This paper introduces Equipotential Learning (EPL), a novel, architecture-agnostic module that improves semantic boundary detection in segmentation tasks by learning decision boundaries through anisotropic field regression and contour learning.

Contribution

It presents the first boundary segmentation method based on field regression and contour learning, enhancing existing models without additional parameters.

Findings

Significant improvements on Pascal VOC 2012 and Cityscapes datasets.

EPL enhances boundary recognition for similar and irregular-shaped categories.

The module is compatible with most existing segmentation architectures.

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 without incurring any parameter overhead. 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.