.png){kind=icon}
返回
Lightweight boundary refinement module based on point supervision for semantic segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.imavis.2021.104169.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
An effective semantic segmentation approach should contain fine object boundaries and continuous regions. However, recent mask-based segmentation cannot extract boundary features well on the coarse prediction, which causes obvious problems of blurry edges. Although several segmentation methods embed boundary de-tection branch to calculate contours directly, this type of architecture will lead to the increased computational complexity and miss the edge detailed information such as inter-class distinction. In order to obtain fine boundaries, we present a lightweight boundary refinement module with point supervision named BRPS to im-prove the boundary quality for the segmentation result generated by various existing segmentation models. Firstly, a direction field is learned to complete the initial feature rectification, which is defined as pointing away from the nearest object boundary to each pixel, where the weighted Euclidean and Cosine distance func-tion is used as the loss between predicted boundary pixels and Ground-truth labels. Then, point-based super-vised learning is performed at uncertain and certain locations including random distribution and key feature points based on a new point convolutional operation to output final crisp object boundaries. Finally, we verify that our BRPS module can effectively reduce the prediction errors for segmentation results generated from various state-of-the-art models such as DeepLabv3 and HRNet on the Pascal VOC2012, NYUD v2 datasets, City-scapes and BDD100K datasets.& nbsp; (c) 2021 Elsevier B.V. All rights reserved.
Keyword:
Semantic segmentation
Boundary refinement
Point supervision
Point convolution
Direction field
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.2
论文数:
4.1K
被引数:
6.7K
机构
引用论文
Contour-Aware Loss: Boundary-Aware Learning for Salient Object Segmentation轮廓感知损失: 用于显着对象分割的边界感知学习
PREAI
分享收藏Automatic Annotation and Segmentation of Object Instances With Deep Active Curve Network.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏