Contextual Exemplar Classifier-Based Image Representation for Classification
Contextual Exemplar Classifier-Based Image Representation for Classification
复制标题
基于上下文样本分类器的图像表示进行分类
DOI：
10.1109/tcsvt.2016.2527380
复制
发表时间：
2017-08
期刊：
影响因子：
--
通讯作者：
Qi Tian
中科院分区：
文献类型：
--
作者：
Chunjie Zhang;Qingming Huang;Qi Tian
近年来，使用局部特征来表示图像已经变得很流行。局部特征常用于视觉词袋方案。虽然这种方法被证明是有效的，但它仍然有两个缺点。首先，提取局部特征的局部区域对视觉任务的区别不够。因此，结合地方特色是必要的。其次，视觉特征与人类感知之间的语义差距也阻碍了性能。为了解决这两个问题，本文提出了一种新的基于上下文范例分类器的图像表示方法，并将其应用于分类任务。每个样本分类器被训练来将一个训练图像从其他不同类别的图像中分离出来。我们将每个图像划分为多个区域，并使用这些样本分类器的响应作为图像区域的表示。然后使用混合狄利克雷分布对上下文关系进行建模。使用双层模型来预测具有$L_{2}$约束的图像类别。在自然场景、Caltech-101/256、Flower-17/102和SUN-397数据集上的实验结果表明，该方法能够优于最先进的基于局部特征的图像分类方法。
The use of local features for image representation has become popular in recent years. Local features are often used in the bag-of-visual-words scheme. Although proven effective, this method still has two drawbacks. First, local regions from which local features are extracted are not discriminative enough for visual tasks. Hence, the combination of local features is necessary. Second, the semantic gap between visual features and human perception also hinders the performance. To address these two problems, in this paper, we propose a novel contextual exemplar classifier-based method for image representation and apply it for classification tasks. Each exemplar classifier is trained to separate one training image from the other images of different classes. We partition each image into a number of regions and use the responses of these exemplar classifiers as the image region’s representation. The contextual relationship is then modeled using mixture Dirichlet distributions. A bilayer model is used to predict image classes with $L_{2}$ constraints. Experimental results on the Natural Scene, Caltech-101/256, Flower-17/102, and SUN-397 data sets show that the proposed method is able to outperform the state-of-the-art local feature-based methods for image classification.
登录
查看更多内容
DOI：
10.1109/cvpr.2010.5539967
发表时间：
2010-06
期刊：
2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
影响因子：
--
作者：
Xiao-Tong Yuan;Shuicheng Yan
通讯作者：
Xiao-Tong Yuan;Shuicheng Yan
影响因子：
6
作者：
Chunjie Zhang;J. Liu;Q. Tian;Chao Liang;Qingming Huang
通讯作者：
Chunjie Zhang;J. Liu;Q. Tian;Chao Liang;Qingming Huang
DOI：
10.1109/cvpr.2010.5539917
发表时间：
2010-06
期刊：
2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
影响因子：
--
作者：
Nianhua Xie;Haibin Ling;Weiming Hu;Xiaoqin Zhang
通讯作者：
Nianhua Xie;Haibin Ling;Weiming Hu;Xiaoqin Zhang
DOI：
10.1109/cvpr.2009.5206594
发表时间：
2009-06
期刊：
2009 IEEE Conference on Computer Vision and Pattern Recognition
影响因子：
--
作者：
Christoph H. Lampert;H. Nickisch;S. Harmeling
通讯作者：
Christoph H. Lampert;H. Nickisch;S. Harmeling
影响因子：
7.3
作者：
Alexander Hauptmann;Rong Yan;Wei-Hao Lin;Michael G. Christel;H. Wactlar
通讯作者：
Alexander Hauptmann;Rong Yan;Wei-Hao Lin;Michael G. Christel;H. Wactlar