• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>SIBGRAPI Conference on Graphics, Patterns and Images >Kernel Approximations for W-Operator Learning
【24h】

Kernel Approximations for W-Operator Learning

机译：W操作员学习的内核近似

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Designing image operators is a hard task usually tackled by specialists in image processing. An alternative approach is to use machine learning to estimate local transformations, that characterize the image operators, from pairs of input-output images. The main challenge of this approach, called W-operator learning, is estimating operators over large windows without overfitting. Current techniques require the determination of a large number of parameters to maximize the performance of the trained operators. Support Vector Machines are known for their generalization performance and their ability to estimate nonlinear decision surfaces using kernels. However, training kernelized SVMs in the dual is not feasible when the training set is large. We estimate the local transformations employing kernel approximations to train SVMs, thus with no need to compute the full Gram matrix. We also select appropriate kernels to process binary and gray level inputs. Experiments show that operators trained using kernel approximation achieve comparable results with state-of-the-art methods in 4 public datasets.
机译：设计图像操作员是一项艰巨的任务，通常由图像处理专家来解决。一种替代方法是使用机器学习从输入/输出图像对中估计表征图像运算符的局部变换。这种方法的主要挑战（称为W-operator学习）是在较大的窗口范围内估算操作员，而不要过度拟合。当前的技术需要确定大量参数以最大化训练有素的操作员的性能。支持向量机以其泛化性能和使用核估计非线性决策面的能力而闻名。但是，当训练集很大时，在双重训练中训练带内核的SVM是不可行的。我们估计采用核逼近来训练SVM的局部变换，因此无需计算完整的Gram矩阵。我们还选择适当的内核来处理二进制和灰度级输入。实验表明，使用核逼近训练的算子在4个公开数据集中使用最新技术可获得可比的结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号