Evaluating Spatial Configuration Constrained CNNs for Localizing Facial and Body Pose Landmarks

Christian Payer, D. Štern, M. Urschler
{"title":"Evaluating Spatial Configuration Constrained CNNs for Localizing Facial and Body Pose Landmarks","authors":"Christian Payer, D. Štern, M. Urschler","doi":"10.1109/IVCNZ48456.2019.8961000","DOIUrl":null,"url":null,"abstract":"Landmark localization is a widely used task required in medical image analysis and computer vision applications. Formulated in a heatmap regression framework, we have recently proposed a CNN architecture that learns on its own to split the localization task into two simpler sub-problems, dedicating one component to locally accurate but ambiguous predictions, while the other component improves robustness by incorporating the spatial configuration of landmarks to remove ambiguities. We learn this simplification in our SpatialConfiguration-Net (SCN) by multiplying the heatmap predictions of its two components and by training the network in and end-to-end manner, thus achieving regularization similar to e.g. a hand-crafted Markov Random Field model. While we have previously shown localization results solely on data from 2D and 3D medical imaging modalities, in this work our aim is to study the generalization capabilities of our SpatialConfiguration-Net to computer vision problems. Therefore, we evaluate our performance both in terms of accuracy and robustness on a facial alignment task, where we improve upon the state-of-the-art methods, as well as on a human body pose estimation task, where we demonstrate results in line with the recent state-of-the-art.","PeriodicalId":217359,"journal":{"name":"2019 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 International Conference on Image and Vision Computing New Zealand (IVCNZ)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IVCNZ48456.2019.8961000","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Landmark localization is a widely used task required in medical image analysis and computer vision applications. Formulated in a heatmap regression framework, we have recently proposed a CNN architecture that learns on its own to split the localization task into two simpler sub-problems, dedicating one component to locally accurate but ambiguous predictions, while the other component improves robustness by incorporating the spatial configuration of landmarks to remove ambiguities. We learn this simplification in our SpatialConfiguration-Net (SCN) by multiplying the heatmap predictions of its two components and by training the network in and end-to-end manner, thus achieving regularization similar to e.g. a hand-crafted Markov Random Field model. While we have previously shown localization results solely on data from 2D and 3D medical imaging modalities, in this work our aim is to study the generalization capabilities of our SpatialConfiguration-Net to computer vision problems. Therefore, we evaluate our performance both in terms of accuracy and robustness on a facial alignment task, where we improve upon the state-of-the-art methods, as well as on a human body pose estimation task, where we demonstrate results in line with the recent state-of-the-art.
评估空间配置约束cnn定位面部和身体姿势地标
在医学图像分析和计算机视觉应用中,地标定位是一项应用广泛的任务。在热图回归框架中,我们最近提出了一种CNN架构,它可以自己学习将定位任务分成两个更简单的子问题,将一个组件用于局部准确但模糊的预测,而另一个组件通过结合地标的空间配置来消除模糊性来提高鲁棒性。我们在我们的SpatialConfiguration-Net (SCN)中学习这种简化,方法是将其两个组件的热图预测乘以,并以端到端方式训练网络,从而实现类似于手工制作的马尔可夫随机场模型的正则化。虽然我们之前只展示了2D和3D医学成像模式数据的定位结果,但在这项工作中,我们的目标是研究我们的SpatialConfiguration-Net对计算机视觉问题的泛化能力。因此,我们在面部对齐任务的准确性和鲁棒性方面评估了我们的表现,其中我们改进了最先进的方法,以及在人体姿势估计任务中,我们展示了与最新技术一致的结果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
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