CNN-based Semantic Segmentation using Level Set Loss

by   Youngeun Kim, et al.

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.



There are no comments yet.


page 1

page 3

page 4

page 8


Multiphase Level-Set Loss for Semi-Supervised and Unsupervised Segmentation with Deep Learning

Recent state-of-the-art image segmentation algorithms are mostly based o...

DV3+HED+: A DCNNs-based Framework to Monitor Temporary Works and ESAs in Railway Construction Project Using VHR Satellite Images

Current VHR(Very High Resolution) satellite images enable the detailed m...

Adversarial Structure Matching Loss for Image Segmentation

The per-pixel cross-entropy loss (CEL) has been widely used in structure...

Highly Efficient Follicular Segmentation in Thyroid Cytopathological Whole Slide Image

In this paper, we propose a novel method for highly efficient follicular...

CNN in CT Image Segmentation: Beyound Loss Function for Expoliting Ground Truth Images

Exploiting more information from ground truth (GT) images now is a new r...

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

We propose a novel, connectivity-oriented loss function for training dee...

Segmentation with Multiple Acceptable Annotations: A Case Study of Myocardial Segmentation in Contrast Echocardiography

Most existing deep learning-based frameworks for image segmentation assu...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.