.png){kind=icon}
返回
Contextual deconvolution network for semantic segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2019.107152.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we propose a Contextual Deconvolution Network (CDN) and focus on context association in decoder network. Specifically, in upsampling path, we introduce two types of contextual modules to model the interdependencies of features in channel and spatial dimensions respectively. The channel contextual module captures image-level semantic information by aggregating the feature maps across spatial dimensions, and clarifies global ambiguity of features. Meanwhile, the spatial contextual module obtains patch-level semantic context by learning a spatial weight map, and enhance the feature discrimination. We embed the two contextual modules into individual components of the decoder network, thus improving the representation power and gaining more precise segment results. Thorough evaluations are performed on four challenging datasets, i.e., PASCAL VOC 2012, ADE20K, PASCAL-Context and Cityscapes dataset. Our approach achieves competitive performance with state-of-the-art models on PASCAL VOC 2012, ADE20K and Cityscapes dataset, and new state-of-the-art performance on PASCAL-Context dataset. (C) 2019 Published by Elsevier Ltd.
Keyword:
Semantic segmentation
Deconvolution network
Channel contextual module
Spatial contextual module
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:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THV.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏Learning Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection用于目标检测的学习旋转不变和Fisher判别卷积神经网络
PREAI
分享收藏Hierarchically Supervised Deconvolutional Network for Semantic Video SegmentationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏LSI: Latent semantic inference for natural image segmentationLSI: 用于自然图像分割的潜在语义推理PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Multi-scale context for scene labeling via flexible segmentation graph通过灵活的分割图实现场景标记的多尺度上下文PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
没有更多内容
没有更多内容