Encoder-Decoder With Cascaded CRFs for Semantic Segmentation

When dealing with semantic segmentation, how to locate the object boundary information more accurately is a key problem to distinguish different objects better. The existing methods lose some image information more or less in the process of feature extraction, which also includes the boundary and context information. At present, some semantic segmentation methods use CRFs (conditional random fields) to obtain boundary information, but they usually only deal with the final output of the model. In this article, inspired by the skip connection of FCN (Fully convolution network) and the good boundary refinement ability of CRFs, a cascaded CRFs is designed and introduced into the decoder of semantic segmentation model to learn boundary information from multi-layers and enhance the ability of the model in object boundary location. Furthermore, in order to supplement the semantic information of images, the output of the cascaded CRFs is fused with the output of the last decoder, so that the model can enhance the ability of locating the object boundary and get more accurate semantic segmentation results. Finally, a number of experiments on different datasets illustrate the feasibility and efficiency of our method, showing that our method enhances the model's ability to locate target boundary information.

Automated summary

This article proposes a new semantic segmentation method that enhances the model's ability to locate object boundaries by introducing cascaded CRFs into the decoder and fusing the output with the last decoder's output, resulting in more accurate semantic segmentation results.