|
利用部分水平提高支持向量机的正则化的典范转移
Enhancing Exemplar SVMs using Part Level Transfer Regularization |
|
| |
| 课程网址: |
http://videolectures.net/bmvc2012_aytar_transfer_regularization/
|
| 主讲教师: |
Yusuf Aytar
|
| 开课单位: |
牛津大学
|
| 开课时间: |
2012-10-09
|
| 课程语种: |
英语
|
| 中文简介: |
示例 svm (e-vvm, malisiewicz 等人, iccv 2011) 在支持向量机只接受了一个阳性样本的训练, 在对象检测和基于内容的图像检索 (cbir) 等领域找到了应用。基于部件的传输正则化, 它可以提高 e-vvm 的性能, 而额外的成本可以忽略不计。这种增强的 e-svm (ee-svm) 通过轻轻地强制从以前学习的分类器中裁剪的现有分类器部分构造, 提高了 e-svm 的泛化能力。在 cbir 应用程序中, 旨在以类似的姿态检索同一对象类的实例, ee-svm 能够容忍 e-svm 上类内变化和变形程度的提高, 从而增加召回。贡献: (a) 引入 ee-svm 目标功能;(b) 证明 ee-svm 在 cbir e-svm 上的性能有了提高;和, (c) 表明, 这个问题和其他问题的传输正则化和特征增强之间存在等价性, 结果是可以使用标准库优化新的目标函数。定量和定性地对 pascal voc 2007 和 imagenet 数据集进行特定对象检索。与 e-svm 相比, 它实现了显著的性能改进, 更抑制了负检测, 增加了召回次数, 同时保持了同样的培训和测试便利性。
|
| 课程简介: |
Exemplar SVMs (E-SVMs, Malisiewicz et al, ICCV 2011), where a SVM is trained with only a single positive sample, have found applications in the areas of object detection and Content-Based Image Retrieval (CBIR), amongst others.\\ In this paper we introduce a method of part based transfer regularization that boosts the performance of E-SVMs, with a negligible additional cost. This Enhanced E-SVM (EE-SVM) improves the generalization ability of E-SVMs by softly forcing it to be constructed from existing classifier parts cropped from previously learned classifiers. In CBIR applications, where the aim is to retrieve instances of the same object class in a similar pose, the EE-SVM is able to tolerate increased levels of intra-class variation and deformation over E-SVM, and thereby increases recall.\\ We make the following contributions: (a) introduce the EE-SVM objective function; (b) demonstrate the improvement in performance of EE-SVM over E-SVM for CBIR; and, (c) show that there is an equivalence between transfer regularization and feature augmentation for this problem and others, with the consequence that the new objective function can be optimized using standard libraries.\\ EE-SVM is evaluated both quantitatively and qualitatively on the PASCAL VOC 2007 and ImageNet datasets for pose specific object retrieval. It achieves a significant performance improvement over E-SVMs, with greater suppression of negative detections and increased recall, whilst maintaining the same ease of training and testing.
|
| 关 键 词: |
计算机科学; 计算机视觉; 支持向量机
|
| 课程来源: |
视频讲座网
|
| 最后编审: |
2020-05-22：王淑红(课程编辑志愿者)
|
| 阅读次数: |
43
|
|
图 书 馆