语义分割的跨粒度注意网络

Lingyu Zhu, T. Wang, Emre B. Aksu, Joni-Kristian Kämäräinen
{"title":"语义分割的跨粒度注意网络","authors":"Lingyu Zhu, T. Wang, Emre B. Aksu, Joni-Kristian Kämäräinen","doi":"10.1109/ICCVW.2019.00241","DOIUrl":null,"url":null,"abstract":"Despite the remarkable progress of semantic segmentation in recent years, much remains to be addressed in order to achieve better semantic coherence and boundary delineation. In this paper, we propose a novel convolutional neural network (CNN) architecture for semantic segmentation which explicitly addresses these two issues. Specifically, we propose a categorical attention mechanism to propagate consistent category-oriented information across multi-granularity contextual interpretations to close the semantic gap residing in CNN feature hierarchy. This novel design alleviates the semantic information loss during the feature combination and transformation process in decoder network. We further integrate a contour branch in our architecture to enhance the boundary awareness of the semantic feature derived in the form of a novel element-wise contour attention at each level of feature hierarchy. Additionally, we introduce a cross-granularity contour enhancement mechanism to propagate rich boundary cues from early layers to deep layers. We perform extensive quantitative evaluations in close proximity to object boundaries which confirms its superior effectiveness in boundary delineation. These novel mechanisms which boost the essentials in segmentation, i.e., region-wise semantic coherence and accurate object contour localization, allow our architecture \"MeshNet\" to obtain state-of-the-art performance on two challenging datasets, i.e., PASCAL VOC 2012 and Cityscapes.","PeriodicalId":300667,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Cross-Granularity Attention Network for Semantic Segmentation\",\"authors\":\"Lingyu Zhu, T. Wang, Emre B. Aksu, Joni-Kristian Kämäräinen\",\"doi\":\"10.1109/ICCVW.2019.00241\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Despite the remarkable progress of semantic segmentation in recent years, much remains to be addressed in order to achieve better semantic coherence and boundary delineation. In this paper, we propose a novel convolutional neural network (CNN) architecture for semantic segmentation which explicitly addresses these two issues. Specifically, we propose a categorical attention mechanism to propagate consistent category-oriented information across multi-granularity contextual interpretations to close the semantic gap residing in CNN feature hierarchy. This novel design alleviates the semantic information loss during the feature combination and transformation process in decoder network. We further integrate a contour branch in our architecture to enhance the boundary awareness of the semantic feature derived in the form of a novel element-wise contour attention at each level of feature hierarchy. Additionally, we introduce a cross-granularity contour enhancement mechanism to propagate rich boundary cues from early layers to deep layers. We perform extensive quantitative evaluations in close proximity to object boundaries which confirms its superior effectiveness in boundary delineation. These novel mechanisms which boost the essentials in segmentation, i.e., region-wise semantic coherence and accurate object contour localization, allow our architecture \\\"MeshNet\\\" to obtain state-of-the-art performance on two challenging datasets, i.e., PASCAL VOC 2012 and Cityscapes.\",\"PeriodicalId\":300667,\"journal\":{\"name\":\"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)\",\"volume\":\"2 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCVW.2019.00241\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCVW.2019.00241","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

摘要

尽管近年来语义分割取得了显著的进展,但为了实现更好的语义连贯和边界划分,还有很多问题需要解决。在本文中,我们提出了一种新的卷积神经网络(CNN)语义分割架构,明确解决了这两个问题。具体而言,我们提出了一种分类注意机制,在多粒度上下文解释中传播一致的面向类别的信息,以缩小存在于CNN特征层次中的语义差距。这种新颖的设计减轻了解码器网络在特征组合和转换过程中语义信息的丢失。我们进一步在我们的架构中集成了一个轮廓分支,以增强语义特征的边界意识,这些语义特征在特征层次的每个层次上以新颖的元素明智的轮廓关注的形式派生。此外,我们引入了一种跨粒度轮廓增强机制,将丰富的边界线索从早期层传播到深层。我们在靠近物体边界的地方进行了广泛的定量评估,这证实了它在边界划定方面的优越有效性。这些新机制提高了分割的基本要素,即区域语义一致性和精确的物体轮廓定位,使我们的架构“MeshNet”能够在两个具有挑战性的数据集(即PASCAL VOC 2012和cityscape)上获得最先进的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Cross-Granularity Attention Network for Semantic Segmentation
Despite the remarkable progress of semantic segmentation in recent years, much remains to be addressed in order to achieve better semantic coherence and boundary delineation. In this paper, we propose a novel convolutional neural network (CNN) architecture for semantic segmentation which explicitly addresses these two issues. Specifically, we propose a categorical attention mechanism to propagate consistent category-oriented information across multi-granularity contextual interpretations to close the semantic gap residing in CNN feature hierarchy. This novel design alleviates the semantic information loss during the feature combination and transformation process in decoder network. We further integrate a contour branch in our architecture to enhance the boundary awareness of the semantic feature derived in the form of a novel element-wise contour attention at each level of feature hierarchy. Additionally, we introduce a cross-granularity contour enhancement mechanism to propagate rich boundary cues from early layers to deep layers. We perform extensive quantitative evaluations in close proximity to object boundaries which confirms its superior effectiveness in boundary delineation. These novel mechanisms which boost the essentials in segmentation, i.e., region-wise semantic coherence and accurate object contour localization, allow our architecture "MeshNet" to obtain state-of-the-art performance on two challenging datasets, i.e., PASCAL VOC 2012 and Cityscapes.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书