CNN-based Semantic Segmentation using Level Set Loss

TL;DR

This paper introduces a novel level set loss function for CNN-based semantic segmentation that enhances spatial detail preservation, especially for small objects and boundaries, by combining variational level set theory with deep learning.

Contribution

The paper proposes a new level set loss function integrated with CNN training to improve spatial detail in segmentation results, addressing limitations of low-resolution CNN outputs.

Findings

Improved boundary accuracy in segmentation results.

Better preservation of small objects and fine details.

Enhanced performance over previous loss functions.

Abstract

Thesedays, Convolutional Neural Networks are widely used in semantic segmentation. However, since CNN-based segmentation networks produce low-resolution outputs with rich semantic information, it is inevitable that spatial details (e.g., small bjects and fine boundary information) of segmentation results will be lost. To address this problem, motivated by a variational approach to image segmentation (i.e., level set theory), we propose a novel loss function called the level set loss which is designed to refine spatial details of segmentation results. To deal with multiple classes in an image, we first decompose the ground truth into binary images. Note that each binary image consists of background and regions belonging to a class. Then we convert level set functions into class probability maps and calculate the energy for each class. The network is trained to minimize the weighted sum of the level set loss and the cross-entropy loss. The proposed level set loss improves the spatial details of segmentation results in a time and memory efficient way. Furthermore, our experimental results show that the proposed loss function achieves better performance than previous approaches.