arrow
返回

Generating crisp boundaries using multi-scale features and mixed loss function

delete2024-08-27
delete0
PRE
AI
C
Changsong Liu
W
Wei Zhang
刘妍妍 封面图
刘妍妍 (Yanyan Liu) *
Y
Yuming Li
DOI:10.1007/s10489-024-05784-5delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Recently, boundary or edge detection has made great progress under the development of convolutional neural networks (CNNs), and some algorithms have achieved a beyond human-level performance. However, CNNs tend to generate blurred edge maps, and their boundary lines are very thick and noisy. In this work, we propose a method named GCB-Net to address this problem. The GCB-Net adopts a simple yet effective fully convolutional U-shape encoder-decoder architecture, with the encoder built on VGG-16 and a novel decoder comprising a feature enhancement module (FEM) and a feature fusion module (FFM). This setup allows our method to produce more discriminative multi-scale features and leverage them for edge detection effectively. Additionally, we construct a novel mixed loss function based on Tversky index, which can guide the network to generate high-quality and crisp edge maps without postprocessing. The experiment results illustrate that the GCB-Net not only enhances the visual effect of edge maps, but also achieves a top performance among several state-of-the-art methods on the BSDS500 dataset (ODS F-score is 0.824) and NYUD-V2 dataset (ODS F-score is 0.766). Our codes are available at https://github.com/AlbertTJU/GCB-Net.
Keyword:
Edge detection
Convolutional neural network
Feature enhancement module
Feature fusion module

期刊

Applied Intelligence 封面图
Applied Intelligence
IF:
3.5
论文数:
7.6K
被引数:
1.7W

机构

T
tianjin university
学者数:
8.0W
论文数: 5.8W
被引数: 88
N
nankai university
学者数:
4.8W
论文数: 3.3W
被引数: 74
引用论文

引用论文

err分享
err收藏
学者 查看更多内容