Locally Shared Features: An Efficient Alternative to Conditional Random Field for Semantic Segmentation

Abstract

In recent years, semantic segmentation methods based on fully convolutional networks (FCNs) have achieved great success. However, these methods tend to produce inconsistency and isolated class labels, mainly because the end-to-end mapping of FCN essentially treats each pixel independently. As a post-processing approach, the conditional random field (CRF) has been widely used to alleviate this problem. However, the inference of CRF is usually very time-consuming in computation. To solve this problem, we present a new method, called locally shared features (LSFs), to model local dependence between pixels. The LSF encourages adjacent pixels to have similar features by making them share certain properties with each other. This is achieved by concatenating features around a pixel, including the pixel itself. Our experimental results indicate—the LSF approach delivers comparable or better performance than the CRF method with respect to the accuracy and local smoothness in segmentation output, while obtaining a significant gain in computational efficiency.

Keywords

• Semantic segmentation
• fully convolutional networks
• feature learning
• context exploitation