A Regularized Convolutional Neural Network for Semantic Image Segmentation

TL;DR

This paper introduces a method to incorporate spatial regularization, like total variation, into CNNs for semantic image segmentation, improving accuracy and noise robustness in models like Unet and Segnet.

Contribution

The paper presents a novel way to integrate spatial regularization into CNNs for segmentation, enhancing their performance and robustness.

Findings

Regularized CNNs outperform original models in segmentation accuracy.

Incorporating spatial regularization improves noise robustness.

Method applied successfully to Unet and Segnet architectures.

Abstract

Convolutional neural networks (CNNs) show outstanding performance in many image processing problems, such as image recognition, object detection and image segmentation. Semantic segmentation is a very challenging task that requires recognizing, understanding what's in the image in pixel level. Though the state of the art has been greatly improved by CNNs, there is no explicit connections between prediction of neighbouring pixels. That is, spatial regularity of the segmented objects is still a problem for CNNs. In this paper, we propose a method to add spatial regularization to the segmented objects. In our method, the spatial regularization such as total variation (TV) can be easily integrated into CNN network. It can help CNN find a better local optimum and make the segmentation results more robust to noise. We apply our proposed method to Unet and Segnet, which are well established CNNs for image segmentation, and test them on WBC, CamVid and SUN-RGBD datasets, respectively. The results show that the regularized networks not only could provide better segmentation results with regularization effect than the original ones but also have certain robustness to noise.