CNN-based Semantic Segmentation using Level Set Loss

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.

2019 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2019

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Image Segmentation by Using Threshold Techniques
• Learning a Discriminative Feature Network for Semantic Segmentation
• Locally Adaptive Learning Loss for Semantic Image Segmentation