Deep Free-Form Deformation Network for Object-Mask Registration

Haoyang Zhang, Xuming He
{"title":"Deep Free-Form Deformation Network for Object-Mask Registration","authors":"Haoyang Zhang, Xuming He","doi":"10.1109/ICCV.2017.456","DOIUrl":null,"url":null,"abstract":"This paper addresses the problem of object-mask registration, which aligns a shape mask to a target object instance. Prior work typically formulate the problem as an object segmentation task with mask prior, which is challenging to solve. In this work, we take a transformation based approach that predicts a 2D non-rigid spatial transform and warps the shape mask onto the target object. In particular, we propose a deep spatial transformer network that learns free-form deformations (FFDs) to non-rigidly warp the shape mask based on a multi-level dual mask feature pooling strategy. The FFD transforms are based on B-splines and parameterized by the offsets of predefined control points, which are differentiable. Therefore, we are able to train the entire network in an end-to-end manner based on L2 matching loss. We evaluate our FFD network on a challenging object-mask alignment task, which aims to refine a set of object segment proposals, and our approach achieves the state-of-the-art performance on the Cityscapes, the PASCAL VOC and the MSCOCO datasets.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"19 1","pages":"4261-4269"},"PeriodicalIF":0.0000,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE International Conference on Computer Vision (ICCV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCV.2017.456","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10

Abstract

This paper addresses the problem of object-mask registration, which aligns a shape mask to a target object instance. Prior work typically formulate the problem as an object segmentation task with mask prior, which is challenging to solve. In this work, we take a transformation based approach that predicts a 2D non-rigid spatial transform and warps the shape mask onto the target object. In particular, we propose a deep spatial transformer network that learns free-form deformations (FFDs) to non-rigidly warp the shape mask based on a multi-level dual mask feature pooling strategy. The FFD transforms are based on B-splines and parameterized by the offsets of predefined control points, which are differentiable. Therefore, we are able to train the entire network in an end-to-end manner based on L2 matching loss. We evaluate our FFD network on a challenging object-mask alignment task, which aims to refine a set of object segment proposals, and our approach achieves the state-of-the-art performance on the Cityscapes, the PASCAL VOC and the MSCOCO datasets.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
对象-掩码配准的深度自由变形网络
本文解决了对象掩码配准问题,该问题将形状掩码与目标对象实例对齐。先前的工作通常将该问题描述为具有掩码先验的对象分割任务,这是一个具有挑战性的解决方案。在这项工作中,我们采用一种基于变换的方法来预测二维非刚性空间变换,并将形状蒙版扭曲到目标物体上。特别地,我们提出了一种深度空间变压器网络,该网络基于多级双掩模特征池化策略,学习自由形式变形(ffd)以非刚性扭曲形状掩模。FFD变换基于b样条,由可微的预定义控制点的偏移量参数化。因此,我们能够以基于L2匹配损失的端到端方式训练整个网络。我们在一个具有挑战性的目标掩码对齐任务上评估了我们的FFD网络,该任务旨在改进一组目标分段建议,我们的方法在cityscape、PASCAL VOC和MSCOCO数据集上实现了最先进的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Visual Odometry for Pixel Processor Arrays Rolling Shutter Correction in Manhattan World Sketching with Style: Visual Search with Sketches and Aesthetic Context Active Learning for Human Pose Estimation Attribute-Enhanced Face Recognition with Neural Tensor Fusion Networks
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1