.png){kind=icon}
返回
Weakly supervised semantic segmentation based on EM algorithm with localization clues
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2017.11.029.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep convolutional neural networks have achieved excellent performance in image semantic segmentation with strong pixel-level annotations. However, pixel-level annotations are very expensive and time-consuming. To overcome this problem, we propose a localization clues guided Expectation-Maximization (LCEM) method to optimize segmentation network parameters with image-level labels. Localization clues provide useful cues to infer pixel labels and guide the Expectation-Maximization (EM) algorithm to more accurate network parameters. The proposed LCEM method consists of three steps: (i) Initialization, (ii) latent posterior estimation with the aid of object localization clues (E step), and (iii) update the network parameters using a new object function that incorporates object clues (M step). We also develop a hybrid training strategy to learn the network parameters. Extensive experimental results validate that the proposed method outperforms current state-of-the-art approaches on the challenging PASCAL VOC 2012 image segmentation benchmark for weakly supervised object segmentation. (c) 2017 Elsevier B.V. All rights reserved.
Keyword:
Semantic segmentation
Weakly supervised
Deep convolutional neural networks
Localization clues
Expectation-Maximization
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:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
.png){kind=icon}
Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images基于学习旋转不变卷积神经网络的VHR光学遥感图像目标检测
PREAI
分享收藏
查看更多内容