Salient object detection via point-to-set metric learning

Salient object detection via point-to-set metric learning
复制标题

通过点对集度量学习进行显着目标检测

DOI:
10.1016/j.patrec.2016.08.018
复制
发表时间:
2016-12
影响因子:
5.1
通讯作者:
Lu Huchuan
Lu Huchuan
中科院分区:
计算机科学3区
文献类型:
--
作者:
You Jia;Zhang Lihe;Qi Jinqing;Lu Huchuan

文献摘要

参考文献

被引文献

相似文献

距离度量是显著目标检测的重要步骤,两两距离通常用于区分显著图像元素(像素和区域)和背景元素。我们没有使用可能隐含地考虑数据点周围上下文信息的点到点距离度量,而是学习了点到集度量来显式地计算单个点到相关点集的距离,并将显著估计转化为点到集分类问题。首先,我们为一幅输入图像(即一些可能包含目标实例的预先检测区域)生成一系列的边界框建议和区域建议,并利用它们计算检索偏好显著图和精度偏好显著图,在此基础上分别确定背景和前景种子区域。然后,采集正负样本(包括点样本和集样本)来学习点到集距离度量,并利用它将图像元素分类为前景类和背景类。最后,对训练样本进行更新,并对分类结果进行细化。在三个具有精确像素标注的大型公开数据集上对所提出的方法进行了评估。大量的实验清楚地证明了所提出的方法相对于最先进的方法的优越性。
Distance metric is an essential step of salient object detection, in which the pairwise distances are often used to distinguish salient image elements (pixels and regions) from background elements. Instead of using the point-to-point distance metrics which possibly implicitly take into account the context information around data points, we learn the point-to-set metric to explicitly compute the distances of single points to sets of correlated points and cast saliency estimation as the problem of point-to-set classification. First, we generate a series of bounding box proposals and region proposals for an input image (i.e., some pre-detected regions which possibly include object instances), and exploit them to compute a recall-preference saliency map and a precision-preference one, based on which the background and foreground seed regions are respectively determined. Next, we collect positive and negative samples (include point samples and set samples) to learn the point-to-set distance metric, and employ it to classify the image elements into foreground and background classes. Last, we update the training samples and refine the classification result. The proposed approach is evaluated on three large publicly available datasets with pixel accurate annotations. Extensive experiments clearly demonstrate the superiority of the proposed approach over the state-of-the-art approaches.
DOI: 10.1109/cvpr.2009.5206596
发表时间: 2009-06
期刊: 2009 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
R. Achanta;S. Hemami;F. Estrada;S. Süsstrunk
通讯作者: R. Achanta;S. Hemami;F. Estrada;S. Süsstrunk
DOI: 10.1109/tpami.2012.89
发表时间: 2013-01-01
影响因子: 23.6
作者:
Borji, Ali;Itti, Laurent
通讯作者: Itti, Laurent
DOI: 10.1109/tpami.2011.272
发表时间: 2012-10-01
影响因子: 23.6
作者:
Goferman, Stas;Zelnik-Manor, Lihi;Tal, Ayellet
通讯作者: Tal, Ayellet
DOI: 10.1109/cvpr.2015.7298937
发表时间: 2015-06
期刊: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子: --
作者:
Jiaping Zhao;Christian Siagian;L. Itti
通讯作者: Jiaping Zhao;Christian Siagian;L. Itti
用于显着性检测的自适应度量学习
DOI: 10.1109/tip.2015.2440755
发表时间: 2015-06
期刊: IEEE Transaction on Image Processing
影响因子: --
作者:
Shuang Li;Huchuan Lu;Zhe Lin;Xiaohui Shen;Brian Price
通讯作者: Brian Price